© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57289
    Prev
    Next
    INDEX
    Explanations

    free shipping and returns

    np_acts-logits-general · gemini-2.5-flash-lite

    free shipping and costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Version
    0.46
     Teacher
    0.46
    t
    0.45
     Xe
    0.44
     Routledge
    0.44
     Exam
    0.43
     twisted
    0.42
    S
    0.42
     used
    0.42
     Weapon
    0.42
    POSITIVE LOGITS
    樂
    0.45
     calific
    0.44
    mailbox
    0.44
     финанси
    0.44
     ܘ
    0.44
    皮膚
    0.44
    kového
    0.44
    蛯
    0.44
    <unused82>
    0.43
    期間
    0.43
    Activations Density 0.002%

    No Known Activations