© 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. 40405
    Prev
    Next
    INDEX
    Explanations

    common observation

    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
    Зна
    0.50
    Beacon
    0.45
     zure
    0.44
    Charm
    0.44
     Nice
    0.43
    urge
    0.42
    极
    0.42
    ት
    0.41
    Solution
    0.41
     aard
    0.41
    POSITIVE LOGITS
    eyse
    0.46
    in
    0.45
    ened
    0.44
     डीपी
    0.44
    linestyle
    0.43
    nV
    0.42
    क्षिक
    0.42
    abilir
    0.42
     NOx
    0.42
     ее
    0.41
    Activations Density 0.003%

    No Known Activations