© 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. 44477
    Prev
    Next
    INDEX
    Explanations

    service, same, $

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

    return and, Saving the, object of

    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
     college
    0.48
     bookmark
    0.45
     tertiary
    0.45
     engineering
    0.45
     CURRENT
    0.44
     metallurgical
    0.43
    t
    0.43
     tiến
    0.43
     current
    0.42
     North
    0.42
    POSITIVE LOGITS
    各式
    0.52
     vadanti
    0.51
    alfi
    0.48
    两者
    0.48
    ጄ
    0.48
     ორი
    0.47
    ăpadă
    0.47
    τευ
    0.46
    Fmat
    0.46
    HasStarred
    0.46
    Activations Density 0.000%

    No Known Activations