© 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. 240384
    Prev
    Next
    INDEX
    Explanations

    Teachers Luncheon

    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
    シャン
    0.53
    s
    0.49
    ってみ
    0.48
    つま
    0.48
    N
    0.48
    ಶ
    0.48
    Most
    0.47
    ים
    0.47
    es
    0.47
    シャ
    0.46
    POSITIVE LOGITS
    ächer
    0.51
     театра
    0.44
     prêts
    0.43
     ഇനി
    0.42
     hopeful
    0.42
    烩
    0.42
    rahman
    0.41
     első
    0.41
     Maroon
    0.41
    illiant
    0.41
    Activations Density 0.001%

    No Known Activations