© 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. 61461
    Prev
    Next
    INDEX
    Explanations

    in some

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

    historical and political conflict

    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
     transportar
    0.43
    🦦
    0.43
     ২০২২
    0.42
     معك
    0.42
     correspondingly
    0.41
     Confidence
    0.41
     می‌باشد
    0.39
     bulunmaktadır
    0.39
     می‌
    0.39
     ejemplo
    0.38
    POSITIVE LOGITS
    ace
    0.47
    lk
    0.43
    reibung
    0.43
    劇情
    0.43
    飭
    0.43
    ian
    0.41
    since
    0.41
    Cllr
    0.41
    img
    0.40
    apt
    0.39
    Activations Density 0.000%

    No Known Activations