© 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. 201127
    Prev
    Next
    INDEX
    Explanations

    details and specifics

    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
     dimensione
    0.51
    প্ট
    0.50
     descubre
    0.49
    zov
    0.48
    quinone
    0.47
    ྟ
    0.46
     useAppContext
    0.46
     construye
    0.46
    相手
    0.46
    intahan
    0.45
    POSITIVE LOGITS
    起
    0.43
     final
    0.43
    оте
    0.41
     shepherd
    0.41
    间隔
    0.41
     HM
    0.41
     Shepherd
    0.40
    Ყ
    0.40
     acquired
    0.40
    éricas
    0.40
    Activations Density 0.004%

    No Known Activations