© 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. 150695
    Prev
    Next
    INDEX
    Explanations

    dedicated to

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

    controversial, foreign words, and math symbols

    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
    에
    0.53
     עם
    0.50
    బ్యా
    0.49
    បែប
    0.48
    인
    0.48
    ക്ക്
    0.48
    आयु
    0.48
     Antilles
    0.47
    經歷
    0.47
    આ
    0.47
    POSITIVE LOGITS
     મુદ્
    0.42
     controversial
    0.42
    shr
    0.42
     warts
    0.41
    ↵↵↵
    0.40
    wara
    0.40
     frauds
    0.40
    ные
    0.39
     policy
    0.39
     vested
    0.39
    Activations Density 0.000%

    No Known Activations