© 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. 163596
    Prev
    Next
    INDEX
    Explanations

    with or without notice

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

    blackout, parentheses, low cost

    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
    兵
    0.47
    傲
    0.46
    官
    0.45
    臨時
    0.45
     Álvarez
    0.45
    ਯ
    0.44
     नजदीक
    0.44
    候補
    0.43
    殚
    0.43
    典
    0.43
    POSITIVE LOGITS
     dint
    0.49
    tk
    0.47
     caroten
    0.47
    mao
    0.46
     chloroplast
    0.46
     simili
    0.46
     photosynthetic
    0.46
     zmniejs
    0.46
     muted
    0.45
    nen
    0.45
    Activations Density 0.001%

    No Known Activations