© 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. 3341
    Prev
    Next
    INDEX
    Explanations

    working Poor, financial asset, investment

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

    listing of items or attributes

    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
    skinned
    0.46
     after
    0.45
    +[
    0.44
    glb
    0.42
    po
    0.42
     alternately
    0.42
    mol
    0.41
    rolled
    0.41
    [
    0.41
     muttered
    0.40
    POSITIVE LOGITS
     кеңсе
    0.47
     работ
    0.46
     souha
    0.46
     acuerdos
    0.45
     piensan
    0.42
     pensando
    0.41
     jurisprudence
    0.41
     незакон
    0.41
    엌
    0.41
     конкур
    0.41
    Activations Density 0.000%

    No Known Activations