© 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. 33359
    Prev
    Next
    INDEX
    Explanations

    country names and locations

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

    continuation or explanation

    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
     Homeless
    0.57
     国産
    0.44
     గ్ర
    0.44
    নাথ
    0.44
    গীত
    0.43
     Disability
    0.43
    ོན་
    0.43
     服
    0.42
    ワーク
    0.41
     খ্রিস্ট
    0.41
    POSITIVE LOGITS
    움을
    0.55
    이어
    0.53
     with
    0.50
     as
    0.47
     immaculate
    0.47
    enya
    0.47
    aisa
    0.47
     accro
    0.46
     accesso
    0.46
    anil
    0.46
    Activations Density 0.000%

    No Known Activations