© 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. 225744
    Prev
    Next
    INDEX
    Explanations

    booking artist

    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
    лайн
    0.52
    uşt
    0.50
     rozpozn
    0.49
     biru
    0.47
    renown
    0.46
    ᆹ
    0.46
    leader
    0.44
    ገል
    0.44
    lines
    0.44
    outlined
    0.43
    POSITIVE LOGITS
     જેને
    0.47
     जिनको
    0.47
     সম্মত
    0.44
    ...@
    0.43
    時間を
    0.42
    WaitingTime
    0.42
     време
    0.42
     tarda
    0.42
     wardrobes
    0.41
    त्तों
    0.41
    Activations Density 0.000%

    No Known Activations