© 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. 111911
    Prev
    Next
    INDEX
    Explanations

    legal or personal identity information

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

    responsible for reporting

    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
    k
    0.55
    kN
    0.53
    र
    0.48
     seu
    0.48
     sang
    0.47
     em
    0.46
     barge
    0.46
    ’
    0.46
     series
    0.46
     bent
    0.46
    POSITIVE LOGITS
     pouze
    0.49
     عمليات
    0.47
     ጉዳ
    0.47
    ശാല
    0.47
     پیسې
    0.46
    罟
    0.43
     مطلب
    0.43
    èrement
    0.42
    䒺
    0.42
    ستخدم
    0.42
    Activations Density 0.001%

    No Known Activations