© 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. 43036
    Prev
    Next
    INDEX
    Explanations

    review scores and ratings

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

    number 4

    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
    情報は
    0.44
    ված
    0.40
     Lieberman
    0.40
     disbanded
    0.39
    粎
    0.39
    ：（
    0.38
     summoned
    0.38
    不存在
    0.37
     reunification
    0.37
    ［
    0.37
    POSITIVE LOGITS
     آتش
    0.47
     rì
    0.45
     حيات
    0.44
     particolarmente
    0.43
    সম্প
    0.41
     ervoor
    0.41
    सोलर
    0.40
     যাই
    0.40
    ješ
    0.40
     chắc
    0.39
    Activations Density 0.000%

    No Known Activations