© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66272
    Prev
    Next
    INDEX
    Explanations

    code structure elements

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

    The neuron fires on literal empty-string tokens (e.g. "" or '').

    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
    釭
    -3.03
    朥
    -2.50
    isation
    -2.38
    re
    -2.23
    providedIn
    -2.22
    ;
    -2.14
    牐
    -2.08
     proactively
    -2.05
    觧
    -2.03
    ール
    -2.02
    POSITIVE LOGITS
    ↵
    2.55
    在他
    2.25
     CALIFORNI
    2.23
     begu
    2.22
    ."
    2.22
    牍
    2.17
     maverick
    2.16
    erapeutics
    2.13
     deceit
    2.13
     was
    2.11
    Activations Density 0.003%

    No Known Activations