© 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. 89885
    Prev
    Next
    INDEX
    Explanations

    made, handmade, custom made

    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
    ื่อ
    0.50
     Erz
    0.47
     atuais
    0.46
     लड़की
    0.46
    𝙤
    0.46
     पारिस्थित
    0.45
    िया
    0.45
    ం
    0.45
     स्वतंत्र
    0.45
    ۲۰
    0.44
    POSITIVE LOGITS
     hamilton
    0.48
     kag
    0.47
    pose
    0.46
     pose
    0.46
    \
    0.46
     abnormality
    0.45
     aberration
    0.44
    "
    0.43
     reson
    0.43
     speedometer
    0.43
    Activations Density 0.000%

    No Known Activations