© 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. 124467
    Prev
    Next
    INDEX
    Explanations

    ON SCHOOL

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

    string matching, time, weak

    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
    a
    0.54
     creature
    0.51
    some
    0.50
    the
    0.48
     Beasts
    0.47
    there
    0.46
     Nintendo
    0.44
     some
    0.44
     }^{\
    0.44
    u
    0.44
    POSITIVE LOGITS
    的研究
    0.61
    焕
    0.54
     نوفمبر
    0.50
     kasarigan
    0.46
    loed
    0.45
     مارس
    0.45
     nooit
    0.45
     تعدى
    0.45
    ٤
    0.44
    يس
    0.44
    Activations Density 0.001%

    No Known Activations