© 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. 116859
    Prev
    Next
    INDEX
    Explanations

    rejected or drawing

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

    strongest language english

    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
    -
    0.56
     pubescence
    0.49
     pike
    0.49
     distinctions
    0.49
     meets
    0.47
     contributors
    0.46
     pubblic
    0.46
     satisfy
    0.45
     linea
    0.45
    オール
    0.45
    POSITIVE LOGITS
    ̹
    0.46
     એન
    0.46
     Cristó
    0.45
    ."))
    0.43
    预算
    0.43
     sluč
    0.42
    бан
    0.42
     cơm
    0.42
    尣
    0.42
    )，
    0.42
    Activations Density 0.000%

    No Known Activations