© 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. 153968
    Prev
    Next
    INDEX
    Explanations

    post, shortlist, take, books, existing

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

    continued contribution

    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
     அல்லது
    0.57
     ಅಥವಾ
    0.46
    น
    0.46
     tige
    0.46
     ngunit
    0.46
     கொல்ல
    0.45
     மற்றும்
    0.45
    或者
    0.44
    หรือ
    0.43
    >?,
    0.43
    POSITIVE LOGITS
     Еўропы
    0.50
     Sociology
    0.46
     lyd
    0.43
     ideologies
    0.42
     revise
    0.42
     오는
    0.41
     Constit
    0.40
     Simply
    0.38
     договора
    0.38
    过来
    0.38
    Activations Density 0.001%

    No Known Activations