© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75318
    Prev
    Next
    INDEX
    Explanations

    further information

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on the discourse marker “Further” (as in “Further,”) at the start of sentences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    formal, sentence-initial additive transitions that introduce an additional point in technical or academic prose

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "Further" followed by a comma in formal technical or scientific writing.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⢊
    -1.90
    (!__
    -1.88
    ":
    -1.72
    𓇼
    -1.69
    鱨
    -1.65
     tempel
    -1.64
     latine
    -1.63
    ]");
    -1.62
     tambien
    -1.59
     nara
    -1.57
    POSITIVE LOGITS
     hallowed
    2.28
     the
    1.95
     facendo
    1.83
     Dritten
    1.82
    因為
    1.72
     attraverso
    1.70
    $
    1.67
    鰨
    1.66
     importantly
    1.66
     renegade
    1.64
    Activations Density 0.008%

    No Known Activations