© 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. 158633
    Prev
    Next
    INDEX
    Explanations

    business services and risks

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

    controlling or search interface

    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
    sms
    0.49
    مان
    0.48
     avatar
    0.47
    uhi
    0.46
     wavenumber
    0.46
    ሙ
    0.46
    πού
    0.45
    remmo
    0.45
    username
    0.45
    avatar
    0.44
    POSITIVE LOGITS
    бира
    0.52
    溅
    0.47
     nere
    0.46
     Periodic
    0.46
     nel
    0.45
     Diving
    0.45
     sporad
    0.45
     uter
    0.44
    IGENCE
    0.44
     Central
    0.43
    Activations Density 0.000%

    No Known Activations