© 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. 62917
    Prev
    Next
    INDEX
    Explanations

    table names and columns

    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
    レベル
    0.49
    ራሉ
    0.46
    pyrrol
    0.44
    ી
    0.44
    utako
    0.44
    withTrashed
    0.43
    είο
    0.42
    巻
    0.42
    たり
    0.41
    लीवुड
    0.41
    POSITIVE LOGITS
    nel
    0.44
    nt
    0.43
     Hunt
    0.43
    ics
    0.42
    เศ
    0.42
    nts
    0.42
     outperformed
    0.41
    emun
    0.41
     Performs
    0.40
    noe
    0.40
    Activations Density 0.001%

    No Known Activations