© 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. 133942
    Prev
    Next
    INDEX
    Explanations

    an Israeli

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

    cosine similarity measures

    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
    heated
    0.47
    ffected
    0.44
    <0x95>
    0.43
    uire
    0.42
    उत्
    0.42
     hottest
    0.42
    clerc
    0.42
     livre
    0.42
    cary
    0.42
     गुस्से
    0.40
    POSITIVE LOGITS
     Shekhar
    0.50
     제외
    0.48
     sekret
    0.47
     sideWeight
    0.46
     ব্যতীত
    0.46
     szpital
    0.46
     ইহা
    0.45
    %、
    0.44
     متعلقه
    0.44
     সম্ব
    0.43
    Activations Density 0.000%

    No Known Activations