© 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. 241728
    Prev
    Next
    INDEX
    Explanations

    Sophisticated, websites, felt

    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
    iviato
    0.55
    opposition
    0.50
    ildiği
    0.50
    diği
    0.49
    remainder
    0.48
     "????.??.??"]
    0.47
    oppositions
    0.46
    驅
    0.46
    automobile
    0.46
     مدينة
    0.46
    POSITIVE LOGITS
     ALSO
    0.51
     Desk
    0.51
     nuk
    0.50
    TEN
    0.48
     also
    0.46
    SSE
    0.46
     sacs
    0.46
     RE
    0.46
    AST
    0.45
     Também
    0.44
    Activations Density 0.000%

    No Known Activations