© 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. 31-GEMMASCOPE-2-RES-262K
    7. 12326
    Prev
    Next
    INDEX
    Explanations

    citation markers like numbers in brackets

    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
    менова
    0.39
    товой
    0.38
    zeuge
    0.37
     ਅਤੇ
    0.37
     ছয়
    0.37
    ၿ
    0.36
    quinoxalin
    0.36
    UCH
    0.36
    λικό
    0.36
     全
    0.35
    POSITIVE LOGITS
     altres
    0.38
     others
    0.37
     implica
    0.37
     divulgação
    0.36
     #
    0.35
     exceptions
    0.35
     Sant
    0.34
     demais
    0.34
     इतर
    0.34
     لي
    0.33
    Activations Density 0.002%

    No Known Activations