© 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. 236399
    Prev
    Next
    INDEX
    Explanations

    transform your kitchen

    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
     growing
    0.44
     closet
    0.42
    系統
    0.42
    説
    0.42
     बढ़ता
    0.42
     crescente
    0.42
    審
    0.41
     will
    0.41
    äre
    0.41
    स्तर
    0.41
    POSITIVE LOGITS
    _{(
    0.47
    ।-
    0.45
    ())),
    0.44
    dsb
    0.44
    (-(
    0.44
     dạ
    0.44
    ()))
    0.43
    broom
    0.43
    随便
    0.43
    vien
    0.42
    Activations Density 0.000%

    No Known Activations