© 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. 100221
    Prev
    Next
    INDEX
    Explanations

    people and organizations

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

    command and definition structure

    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
    ари
    0.51
    ן
    0.48
    altungen
    0.47
    rin
    0.47
    씀
    0.47
    ån
    0.46
     народ
    0.46
     eğer
    0.46
     وير
    0.46
     عاي
    0.45
    POSITIVE LOGITS
    ئیں۔
    0.42
     手
    0.42
     新
    0.41
     idioms
    0.40
     Xiao
    0.39
     डूब
    0.39
     meaningless
    0.39
    高手
    0.39
    ドラゴン
    0.39
    塞
    0.38
    Activations Density 0.001%

    No Known Activations