© 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. 142153
    Prev
    Next
    INDEX
    Explanations

    Python imports

    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
     போன்றவற்ற
    0.48
     ständig
    0.44
    erol
    0.43
     स्थानिक
    0.43
    ային
    0.43
    परिवार
    0.42
     ağı
    0.42
    🕴
    0.41
    等多
    0.40
    рат
    0.40
    POSITIVE LOGITS
     plead
    0.41
    UMB
    0.39
    HttpDelete
    0.39
    Drum
    0.38
    insol
    0.38
     Drury
    0.37
    ispo
    0.36
    non
    0.36
     blunt
    0.36
    9
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.