© 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. 75729
    Prev
    Next
    INDEX
    Explanations

    is or это followed by a description

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

    The neuron fires on the common “this is a” introductory phrase.

    oai_token-act-pair · o4-miniTriggered 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
    其他
    -1.74
     egyéb
    -1.61
    其它
    -1.55
     issuance
    -1.55
     varandra
    -1.55
     ciepła
    -1.54
    ).
    -1.52
     stagnant
    -1.50
    その他の
    -1.48
     multitude
    -1.47
    POSITIVE LOGITS
     teraz
    1.52
     –
    1.40
     leggero
    1.36
    ization
    1.35
     briefly
    1.31
     happened
    1.31
     the
    1.31
    但不
    1.30
    يم
    1.30
     is
    1.25
    Activations Density 0.007%

    No Known Activations