© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28608
    Prev
    Next
    INDEX
    Explanations

    productive week

    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_40_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
     Leopard
    0.42
    爱
    0.39
    รา
    0.37
     نق
    0.37
    stractions
    0.37
    ropo
    0.37
    隷
    0.37
    名人
    0.36
     clap
    0.36
    rante
    0.36
    POSITIVE LOGITS
     conversion
    0.40
     bioge
    0.39
     conversión
    0.39
     Aqueous
    0.38
     effectiveness
    0.37
     ہوتی
    0.37
     costas
    0.37
     Simplified
    0.37
     Prefer
    0.37
     Ditto
    0.37
    Activations Density 0.000%

    No Known Activations