© 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. 41357
    Prev
    Next
    INDEX
    Explanations

    citation formatting

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

    bathroom

    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
     रिप्रे
    0.48
     লোকের
    0.46
    िमम
    0.46
     represent
    0.44
     Represent
    0.43
    會在
    0.43
    妽
    0.42
    教會
    0.42
     Contribute
    0.42
    ToExp
    0.41
    POSITIVE LOGITS
    ρι
    0.45
    aired
    0.42
     Sección
    0.42
     hailing
    0.41
     Douglas
    0.41
    棉
    0.40
    적
    0.40
     Jol
    0.40
     defective
    0.39
    放送
    0.38
    Activations Density 0.000%

    No Known Activations