© 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-65K
    7. 3843
    Prev
    Next
    INDEX
    Explanations

    upload, end, home, schedule

    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_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
    ſs
    0.53
     vague
    0.46
    gesterone
    0.45
     extol
    0.45
    ş
    0.44
    şe
    0.43
    amingo
    0.43
    ‡
    0.42
    žad
    0.42
    ouver
    0.41
    POSITIVE LOGITS
    ING
    0.77
    ER
    0.74
    ON
    0.66
    ERS
    0.66
    RE
    0.62
    FORM
    0.60
    IN
    0.59
    IND
    0.59
    VER
    0.59
    ORY
    0.59
    Activations Density 0.198%

    No Known Activations