© 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. 3110
    Prev
    Next
    INDEX
    Explanations

    initials and abbreviations

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

    Street abbreviations

    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
    ⛺
    0.50
    饷
    0.43
    जीलैंड
    0.41
    아요
    0.40
    larınız
    0.40
     സംഘടന
    0.40
    󰀄
    0.39
     ధర
    0.39
     giày
    0.39
     البيانات
    0.39
    POSITIVE LOGITS
    ↵↵
    0.49
    ↵
    0.35
     V
    0.34
    ð
    0.34
     S
    0.34
    ə
    0.33
    št
    0.32
    ](../
    0.32
    his
    0.32
     stellte
    0.32
    Activations Density 0.000%

    No Known Activations