© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61585
    Prev
    Next
    INDEX
    Explanations

    concepts and topic beginnings

    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
    the
    0.62
     the
    0.49
    ↵
    0.46
    serve
    0.46
    tr
    0.44
    The
    0.43
    details
    0.43
    ip
    0.43
    A
    0.42
    degree
    0.42
    POSITIVE LOGITS
    CreateWall
    0.59
     कमि
    0.47
    🚮
    0.46
    出力
    0.44
    FolderPath
    0.44
    ፈላጊ
    0.43
    alámb
    0.43
     яичко
    0.43
    Hound
    0.42
     carpentry
    0.42
    Activations Density 0.016%

    No Known Activations