© 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. 144705
    Prev
    Next
    INDEX
    Explanations

    'description:' or 'describe'

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

    test descriptions initiated by describe

    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
    dır
    0.48
     sift
    0.47
     मुझसे
    0.47
    stove
    0.46
     sketches
    0.46
     than
    0.46
     cared
    0.46
     ތ
    0.44
    nis
    0.43
     skepticism
    0.43
    POSITIVE LOGITS
    езд
    0.50
    EditorGUI
    0.48
    ブロック
    0.47
    ваю
    0.47
    бо
    0.47
    рного
    0.46
    거
    0.46
    μα
    0.46
    ινων
    0.46
    ме
    0.46
    Activations Density 0.000%

    No Known Activations