© 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. 34-GEMMASCOPE-RES-131K
    7. 23608
    Prev
    Next
    INDEX
    Explanations

    password/reset token

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

    The neuron fires on multi‐digit numeric tokens (i.e. sequences of digits such as line numbers, IDs, version codes, etc.).

    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
     thousands
    -0.65
    NSMutableArray
    -0.63
     foreign
    -0.63
     persuaded
    -0.60
     hundreds
    -0.59
    資本
    -0.59
     Lich
    -0.59
     vnd
    -0.58
    льному
    -0.58
     omitted
    -0.58
    POSITIVE LOGITS
    ERV
    0.75
    teren
    0.75
    strada
    0.71
    Gam
    0.70
     Tours
    0.69
    CTX
    0.69
     gata
    0.68
    ≖
    0.68
    receptor
    0.68
    Dice
    0.68
    Activations Density 0.072%

    No Known Activations