© 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. 224540
    Prev
    Next
    INDEX
    Explanations

    understand how things are shaped

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

    definitions or descriptions

    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
     poeta
    0.51
     போன
    0.49
     catcher
    0.48
    parseDouble
    0.47
     ferrugineux
    0.47
     comprising
    0.45
    てもら
    0.45
    ”;
    0.45
    niest
    0.45
    に限
    0.45
    POSITIVE LOGITS
    shapes
    0.47
     شکل
    0.46
    Shapes
    0.45
    Rogers
    0.45
     shapes
    0.41
    ک
    0.41
     reshaping
    0.40
    也許
    0.40
    جن
    0.40
    دم
    0.39
    Activations Density 0.001%

    No Known Activations