© 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. 11122
    Prev
    Next
    INDEX
    Explanations

    The luxury vehicle

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

    lettuce turn over a new leaf

    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
    プリン
    0.41
    逶
    0.40
    Principles
    0.40
    बॉलीवुड
    0.39
     నిర్
    0.39
    ौन
    0.38
     चव्हाण
    0.38
    ױ
    0.38
     அவர்களுடைய
    0.38
    मेरे
    0.38
    POSITIVE LOGITS
    fs
    0.43
    fk
    0.41
     finish
    0.40
     finishing
    0.39
    finish
    0.39
    iasi
    0.39
    nk
    0.38
    cdc
    0.38
    cdf
    0.38
    sf
    0.37
    Activations Density 0.001%

    No Known Activations