© 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. 95242
    Prev
    Next
    INDEX
    Explanations

    states and locations

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

    datasets import

    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
     getDefault
    0.49
     самое
    0.49
    కొ
    0.48
     निजात
    0.45
    Насе
    0.45
    d
    0.45
    ziest
    0.44
    蹉
    0.44
    褻
    0.44
    də
    0.43
    POSITIVE LOGITS
     imping
    0.47
     soport
    0.46
    ین
    0.46
     بازیکن
    0.46
    ীব্র
    0.45
    球员
    0.45
     afet
    0.44
    usuario
    0.44
     mann
    0.44
     seleção
    0.44
    Activations Density 0.000%

    No Known Activations