© 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. 59802
    Prev
    Next
    INDEX
    Explanations

    overall structure and appearance

    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
    algèbre
    0.48
     ብ
    0.48
    FromArray
    0.46
     anisotropy
    0.44
     automaker
    0.44
     सय
    0.44
     верхней
    0.44
    arra
    0.43
    aların
    0.43
    атр
    0.43
    POSITIVE LOGITS
    2
    0.50
     सीजी
    0.49
    will
    0.48
     svoje
    0.48
     tendrá
    0.47
     akan
    0.46
    7
    0.46
    he
    0.45
     untuk
    0.45
     will
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.