© 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. 116013
    Prev
    Next
    INDEX
    Explanations

    specific physical requirements

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

    cultural heritage

    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
    ων
    0.48
    BOOK
    0.48
    UOUS
    0.46
    ^{*}$
    0.45
    ত্তম
    0.43
    жную
    0.43
    чити
    0.43
    贅
    0.43
    ную
    0.43
    ブック
    0.42
    POSITIVE LOGITS
    ת
    0.53
     sim
    0.52
    ت
    0.49
     لن
    0.47
     funktion
    0.47
     modific
    0.47
     sqrt
    0.47
    لما
    0.46
     copi
    0.46
     indic
    0.45
    Activations Density 0.001%

    No Known Activations