© 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. 260900
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    昃
    0.56
    สนามกีฬา
    0.52
    枻
    0.52
    氳
    0.51
    ปี
    0.51
    俅
    0.49
     воды
    0.49
    涘
    0.49
    ტრ
    0.48
    ร
    0.48
    POSITIVE LOGITS
    ans
    0.57
    alee
    0.57
    in
    0.56
    ana
    0.55
    akin
    0.54
    ab
    0.54
    ah
    0.53
     volatile
    0.53
    a
    0.53
    us
    0.52
    Activations Density 0.000%

    No Known Activations