© 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. 133492
    Prev
    Next
    INDEX
    Explanations

    events will, last week

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

    edge attributes and weights

    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
     saliva
    0.52
     licensee
    0.50
     release
    0.49
    /
    0.49
     PST
    0.49
     strict
    0.47
    <sup>
    0.46
     protective
    0.46
     legalization
    0.46
     refueling
    0.45
    POSITIVE LOGITS
    िक
    0.51
     ກ
    0.50
    昷
    0.50
     ונ
    0.49
     Yukarı
    0.47
    উদাহরণ
    0.47
    ונ
    0.46
     شی
    0.46
    getType
    0.46
    㐸
    0.46
    Activations Density 0.000%

    No Known Activations