© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 23468
    Prev
    Next
    INDEX
    Explanations

    to be

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

    first public; starting number; two leading

    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
    UIC
    0.47
    wstring
    0.45
    leur
    0.45
    DC
    0.44
    <0x0D>
    0.43
     UIC
    0.43
     cyst
    0.42
     well
    0.42
    </h3>
    0.41
    .
    0.40
    POSITIVE LOGITS
    เพื่อ
    0.45
    是因為
    0.44
     najman
    0.44
     إدارة
    0.44
     মালা
    0.43
     Anya
    0.42
    蛙
    0.42
     ملا
    0.40
     प्राथमिकता
    0.40
    ระยะ
    0.40
    Activations Density 0.000%

    No Known Activations