© 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. 36504
    Prev
    Next
    INDEX
    Explanations

    PHP models and shell commands

    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
     chiropractor
    0.43
    出于
    0.42
    蒌
    0.42
    avigation
    0.42
    HeaderAccept
    0.40
    asiti
    0.40
    stylesheets
    0.39
    ো
    0.38
    inputSet
    0.38
    平方米
    0.38
    POSITIVE LOGITS
     CES
    0.42
     Penal
    0.41
     TS
    0.40
    dater
    0.40
    Dell
    0.39
     Fare
    0.38
     ts
    0.38
     Passage
    0.37
     Connect
    0.37
    dell
    0.37
    Activations Density 0.000%

    No Known Activations