© 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. 97645
    Prev
    Next
    INDEX
    Explanations

    more

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

    first, most, assault

    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
    قیه
    0.41
     colaboración
    0.41
     एसपी
    0.40
    𝙎
    0.40
     colaborar
    0.40
    뿍
    0.39
     Spielen
    0.39
     പി
    0.39
     Spell
    0.38
     fla
    0.38
    POSITIVE LOGITS
    agt
    0.45
    粽
    0.42
    HHHH
    0.41
    ول
    0.41
    effect
    0.40
    怎
    0.40
    垍
    0.40
     किस
    0.39
    どのように
    0.39
    ح
    0.39
    Activations Density 0.000%

    No Known Activations