© 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. 80672
    Prev
    Next
    INDEX
    Explanations

    no obligation to update

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

    del niño

    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
     வித
    0.47
     অর্থে
    0.42
    諮
    0.42
    ぽ
    0.41
     வக
    0.41
    谘
    0.41
     prosper
    0.41
    ciendo
    0.40
    proper
    0.40
     ومع
    0.40
    POSITIVE LOGITS
    Waterfall
    0.56
    굵
    0.50
    ക്തി
    0.49
     原子
    0.49
     Waterfall
    0.48
     更新
    0.48
     атом
    0.48
    Bộ
    0.47
    Internal
    0.47
    Компания
    0.47
    Activations Density 0.001%

    No Known Activations