© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2310
    Prev
    Next
    INDEX
    Explanations

    code syntax surrounding blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    ნდა
    0.48
    .*;
    0.47
    ینګ
    0.46
    [,]
    0.46
    .
    0.46
    น่า
    0.45
    .¹
    0.45
    .[
    0.44
    .*
    0.43
     ikan
    0.43
    POSITIVE LOGITS
    ખ
    0.49
    ↵
    0.43
    чень
    0.41
    seamless
    0.40
    Reporting
    0.40
    muj
    0.39
    щины
    0.39
     timely
    0.38
     उसको
    0.38
    доб
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.