© 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. 110448
    Prev
    Next
    INDEX
    Explanations

    proprietary resource

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

    HTML form action 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
     arrival
    0.44
    жела
    0.44
    ครบ
    0.42
     klik
    0.42
    a
    0.42
     Szer
    0.42
     Ort
    0.41
     Iceland
    0.40
    dr
    0.40
     Vez
    0.40
    POSITIVE LOGITS
    fromj
    0.46
    ubine
    0.45
    回答
    0.45
     เฉ
    0.45
     doenças
    0.44
     tipo
    0.43
     ハ
    0.43
     DREAM
    0.43
     malattia
    0.43
    ষুধ
    0.42
    Activations Density 0.000%

    No Known Activations