© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143600
    Prev
    Next
    INDEX
    Explanations

    lists, descriptions, or code

    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
     agrav
    0.51
    addEdge
    0.49
    രം
    0.48
     inicialmente
    0.45
     integrantes
    0.45
     unripe
    0.45
     الجمهور
    0.44
    }|=
    0.43
     necessidades
    0.43
     insuficiente
    0.42
    POSITIVE LOGITS
     grade
    0.53
    i
    0.53
     RSS
    0.44
    ural
    0.44
    です
    0.44
     leaderboard
    0.44
     Grade
    0.43
    聞
    0.43
     operational
    0.42
     walk
    0.42
    Activations Density 0.003%

    No Known Activations