© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55507
    Prev
    Next
    INDEX
    Explanations

    schema, db, visuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     महत्त्व
    0.41
    Mapping
    0.40
    
    0.38
    mapping
    0.38
    檬
    0.38
    具体的な
    0.38
    Bs
    0.36
    对象的
    0.36
     Soap
    0.36
    Names
    0.36
    POSITIVE LOGITS
     Lynn
    0.37
     trasferimento
    0.37
     Finanz
    0.37
    ัม
    0.36
    د
    0.36
     ingresos
    0.36
    фон
    0.35
     fon
    0.35
     soluzioni
    0.35
     cristal
    0.35
    Activations Density 0.001%

    No Known Activations