© 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. 190302
    Prev
    Next
    INDEX
    Explanations

    roles or status

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

    longest, oldest, greatest

    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
    i
    0.39
     मिश्र
    0.38
     Monday
    0.38
    হাম্ম
    0.38
     Tue
    0.38
     undang
    0.38
    ૅ
    0.38
     skriver
    0.37
     Davenport
    0.37
     enables
    0.37
    POSITIVE LOGITS
    潾
    0.45
    我国
    0.45
    endorong
    0.45
    ೋತಿ
    0.45
    ાર્થી
    0.44
    élect
    0.42
    곧
    0.40
     כל
    0.40
    它的
    0.39
     ہمیشہ
    0.39
    Activations Density 0.001%

    No Known Activations