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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73641
    Prev
    Next
    INDEX
    Explanations

    tokens followed by specific continuations

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

    The neuron fires on uncommon or specialized tokens—especially diacritical characters and low‐frequency technical terms.

    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
     -
    -3.06
    with
    -2.95
    which
    -2.81
    Certainly
    -2.63
    天生
    -2.59
    by
    -2.55
     üblichen
    -2.53
     aña
    -2.52
     zweiten
    -2.48
    ⩴
    -2.47
    POSITIVE LOGITS
    鰱
    2.92
    '
    2.69
    鲥
    2.67
    เกง
    2.64
    呖
    2.58
    餽
    2.48
    鯷
    2.45
    肏
    2.38
     всѣ
    2.36
    踅
    2.33
    Activations Density 0.000%

    No Known Activations