© 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. 40-GEMMASCOPE-2-RES-262K
    7. 130894
    Prev
    Next
    INDEX
    Explanations

    column naming and joining

    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_40_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
    Want
    0.42
    茠
    0.42
    ほう
    0.42
    Types
    0.41
    Checks
    0.41
     দুজন
    0.40
    System
    0.40
    Wonder
    0.39
    Raising
    0.39
    thood
    0.39
    POSITIVE LOGITS
     Column
    0.45
     COLUMN
    0.40
     column
    0.40
    冰
    0.39
     σει
    0.38
    멀
    0.38
     列
    0.38
     ColumnName
    0.38
     solic
    0.38
    避
    0.38
    Activations Density 0.000%

    No Known Activations