© 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. 133604
    Prev
    Next
    INDEX
    Explanations

    specific details or instructions

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

    "own hands", "dared suggest"

    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
    慘
    0.47
    펭
    0.46
    ảm
    0.45
    ίλ
    0.45
    ysets
    0.45
     கெல்
    0.44
     Bxh
    0.44
     hypergeometric
    0.43
    abcd
    0.43
    [{\
    0.43
    POSITIVE LOGITS
    nette
    0.47
     between
    0.46
     بین
    0.46
    前来
    0.46
     at
    0.45
    li
    0.45
    గం
    0.44
    s
    0.44
     เ
    0.44
     그리고
    0.43
    Activations Density 0.001%

    No Known Activations