© 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. 128476
    Prev
    Next
    INDEX
    Explanations

    personalized place

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

    ** such as

    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
    i
    0.63
    as
    0.55
    轵
    0.53
    ي
    0.52
    seeded
    0.52
     Aids
    0.49
    asd
    0.49
    ে
    0.48
    uie
    0.48
     Plugging
    0.48
    POSITIVE LOGITS
    コハマ
    0.46
     ねえ
    0.45
     giáo
    0.44
     retract
    0.44
     まあ
    0.44
     conducts
    0.43
     drows
    0.43
     resides
    0.42
     glittering
    0.42
     flota
    0.42
    Activations Density 0.013%

    No Known Activations