© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48996
    Prev
    Next
    INDEX
    Explanations

    time period followed by event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ר
    0.55
    ע
    0.54
    お
    0.53
    ב
    0.53
    вах
    0.50
    ס
    0.50
    О
    0.50
    С
    0.49
    Türk
    0.49
    По
    0.46
    POSITIVE LOGITS
     Cellulose
    0.54
     algal
    0.52
     phyto
    0.50
     évaluation
    0.49
     Supervisory
    0.48
     auxin
    0.48
     Sequential
    0.47
     hydroelectric
    0.47
     waterfront
    0.47
     Signaling
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.