© 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. 39133
    Prev
    Next
    INDEX
    Explanations

    enter find help inform discovered work again profit fantastic

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

    wife, drain, auger

    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
    哉
    0.45
    SB
    0.45
     notables
    0.44
    必要
    0.43
     fates
    0.43
    дован
    0.43
     automakers
    0.42
     fate
    0.42
     restantes
    0.42
    主
    0.42
    POSITIVE LOGITS
    have
    0.47
    itetty
    0.46
    irittura
    0.46
    vanje
    0.44
    asına
    0.44
     haue
    0.43
    και
    0.43
     have
    0.43
     პირადი
    0.43
    oną
    0.43
    Activations Density 0.000%

    No Known Activations