© 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. 45647
    Prev
    Next
    INDEX
    Explanations

    values, with, stimulates

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

    written by, her invitation

    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
    龴
    0.47
     legislator
    0.47
     contém
    0.46
     propel
    0.46
     hirs
    0.46
     dysph
    0.46
    ্ঠ
    0.45
     hypothalamic
    0.45
    ˛
    0.45
     engineer
    0.45
    POSITIVE LOGITS
    WATER
    0.49
    ز
    0.47
    ways
    0.44
    WEB
    0.44
    unix
    0.44
    fixes
    0.44
    ذف
    0.43
    shortcuts
    0.43
    slag
    0.42
    enar
    0.42
    Activations Density 0.000%

    No Known Activations