© 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. 239481
    Prev
    Next
    INDEX
    Explanations

    processing subjects

    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
    f
    0.50
     Rope
    0.46
    直し
    0.45
     WAIT
    0.45
     Wine
    0.45
     gloomy
    0.44
     サー
    0.44
     BEAR
    0.44
    c
    0.44
    ’
    0.44
    POSITIVE LOGITS
     پاکستانی
    0.52
    粔
    0.52
    ToCheck
    0.49
    .[
    0.48
    Verification
    0.46
     되었다
    0.46
    Verified
    0.44
    Starting
    0.44
    Checks
    0.44
     moeil
    0.43
    Activations Density 0.000%

    No Known Activations