© 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-65K
    7. 27609
    Prev
    Next
    INDEX
    Explanations

    coffee table

    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_65k_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
    atinum
    0.45
    ♒
    0.45
    বিত্র
    0.44
    ност
    0.44
    🚀
    0.44
    ный
    0.43
     మరియు
    0.42
    ቶች
    0.42
    बैक
    0.41
    ០
    0.41
    POSITIVE LOGITS
     rameaux
    0.50
     supplément
    0.45
     spezi
    0.45
     ocasi
    0.45
     spermat
    0.44
     spécialistes
    0.44
     aromat
    0.43
     shrubs
    0.43
     encuentros
    0.42
     peintre
    0.42
    Activations Density 0.011%

    No Known Activations