© 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. 22-GEMMASCOPE-RES-131K
    7. 33138
    Prev
    Next
    INDEX
    Explanations

    section headers or starting phrases

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

    The neuron fires on numeric tokens (digits) embedded in markup or code (e.g. the “6” in “font‐size=16px”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    邉
    -1.11
     moletom
    -1.06
     garansi
    -1.03
    طط
    -1.02
    ähte
    -0.99
     INDUSTRIES
    -0.98
     microfibra
    -0.96
     pastikan
    -0.95
     sitten
    -0.94
    🦈
    -0.94
    POSITIVE LOGITS
    ⩴
    0.97
    ("</
    0.95
    .}\
    0.93
     ausged
    0.91
    poss
    0.89
    Bris
    0.88
    ichert
    0.87
    __':
    0.85
    𖤍
    0.85
    dagog
    0.85
    Activations Density 0.000%

    No Known Activations