© 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. 32928
    Prev
    Next
    INDEX
    Explanations

    sub. `

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

    final answer boxed

    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
    ;
    0.79
     ;
    0.63
    izer
    0.63
    itu
    0.62
    op
    0.57
    ;.
    0.57
    ipp
    0.56
    oh
    0.54
    og
    0.53
    ator
    0.53
    POSITIVE LOGITS
    旣
    0.53
    에
    0.52
    ைத்
    0.50
    箫
    0.48
    𝓟
    0.48
    Эк
    0.48
    셸
    0.47
    ที่
    0.47
     cooperated
    0.46
    ΙΑ
    0.46
    Activations Density 0.000%

    No Known Activations