© 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. 112234
    Prev
    Next
    INDEX
    Explanations

    concept and consequence

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

    super intelligent robot

    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
    fahren
    0.44
     ^^
    0.43
     INDIA
    0.43
    ride
    0.42
    cra
    0.42
     जयपुर
    0.42
     этом
    0.42
     ఇంత
    0.42
     Stakes
    0.41
    .
    0.41
    POSITIVE LOGITS
    人と
    0.55
    ከና
    0.53
     esoteric
    0.48
    インストール
    0.47
     metadata
    0.46
     tabl
    0.46
     audiov
    0.45
     tér
    0.44
     podataka
    0.44
     paradig
    0.44
    Activations Density 0.001%

    No Known Activations