© 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. 39131
    Prev
    Next
    INDEX
    Explanations

    deep blue fabric

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

    knew their, potential for, familiar under

    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
    ανο
    0.51
    三分
    0.49
    探し
    0.49
    透过
    0.48
    三个
    0.46
    ٢
    0.46
    请
    0.46
     stunned
    0.44
    २
    0.44
    ကျော်
    0.44
    POSITIVE LOGITS
     Mysteries
    0.46
     boje
    0.46
    நபியே
    0.45
     vegetal
    0.44
     Azerbaijani
    0.44
    /-}$
    0.42
    سط
    0.42
     கூடிய
    0.42
     مخصوص
    0.42
     আখ
    0.41
    Activations Density 0.001%

    No Known Activations