© 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. 34-GEMMASCOPE-RES-131K
    7. 93512
    Prev
    Next
    INDEX
    Explanations

    part numbers and model codes

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

    The neuron is triggered by numeric or alphanumeric sequences used as part or model numbers (e.g. “5231EL10003B” or “HS8L-DC6V-SC”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     things
    -0.92
     ergän
    -0.90
     Συ
    -0.85
     aukš
    -0.80
     prieš
    -0.80
    fR
    -0.79
     backwards
    -0.78
     stuff
    -0.78
     vė
    -0.77
     Schia
    -0.76
    POSITIVE LOGITS
     #(
    1.02
     salonu
    0.97
    für
    0.95
     sezonu
    0.94
     komis
    0.93
     reklama
    0.88
     adresu
    0.88
    кту
    0.88
     tersenyum
    0.88
    كتاب
    0.87
    Activations Density 0.079%

    No Known Activations