© 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. 47644
    Prev
    Next
    INDEX
    Explanations

    log in or signed out

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

    This neuron fires on occurrences of “log” in various forms (e.g. log, logging, logged) marking mentions of signing in/out.

    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
    moveToNext
    -0.91
     iconLine
    -0.87
    GRACIAS
    -0.81
    chii
    -0.79
     porté
    -0.77
    ſi
    -0.77
    算了
    -0.76
    Dichloroethene
    -0.76
    rant
    -0.74
    teman
    -0.74
    POSITIVE LOGITS
     out
    1.75
     in
    1.58
    out
    1.25
     into
    1.08
    in
    0.96
    Out
    0.89
    OUT
    0.88
     sesión
    0.79
     Gable
    0.77
    caixa
    0.74
    Activations Density 0.015%

    No Known Activations