© 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. 194429
    Prev
    Next
    INDEX
    Explanations

    police station context

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

    based on, used together, initial contact, through dialogue

    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
     Himself
    0.47
     বারবার
    0.46
    lation
    0.45
    祿
    0.44
    phyl
    0.44
    ovec
    0.44
    otherArgs
    0.43
     theorems
    0.43
    strokes
    0.43
     épaules
    0.43
    POSITIVE LOGITS
    얹
    0.46
    뽐
    0.43
    hey
    0.42
    点了点头
    0.42
     are
    0.41
    뒹
    0.41
     stehen
    0.40
     soir
    0.40
     Monterrey
    0.40
     was
    0.39
    Activations Density 0.000%

    No Known Activations