© 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. 196359
    Prev
    Next
    INDEX
    Explanations

    final poll or URL

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

    common phrases and questions

    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
     douche
    0.45
     Yeh
    0.45
    öner
    0.44
     صہی
    0.44
     السنوات
    0.42
    Yeh
    0.41
    纓
    0.41
    zentration
    0.40
    screw
    0.40
     salle
    0.40
    POSITIVE LOGITS
    юнча
    0.47
     posiblemente
    0.47
    P
    0.46
    П
    0.45
    cas
    0.45
    '],
    0.44
    🐟
    0.44
    Cas
    0.44
    勇敢
    0.44
    DOMAIN
    0.43
    Activations Density 0.000%

    No Known Activations