© 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. 110520
    Prev
    Next
    INDEX
    Explanations

    short followed by punctuation

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

    The neuron fires on occurrences of the exact uppercase token “SHORT.”

    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
    簠
    -1.90
     a
    -1.59
    写真を
    -1.55
     ardent
    -1.53
     you
    -1.52
    籥
    -1.51
     uncompromising
    -1.51
    ܜ
    -1.48
     troublesome
    -1.44
     prodigious
    -1.44
    POSITIVE LOGITS
    3
    3.25
    6
    2.94
    9
    2.61
    7
    2.56
    5
    2.55
    8
    2.53
    4
    2.45
    2
    2.31
    '
    1.85
    If
    1.84
    Activations Density 0.000%

    No Known Activations