© 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. 184498
    Prev
    Next
    INDEX
    Explanations

    purchasing, engineering, winning, article, spot

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

    gas laws, mortality rate

    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
     countless
    0.50
     poaching
    0.50
     abatement
    0.49
     scandal
    0.49
     preoccup
    0.49
    ๔
    0.49
     auditing
    0.48
     transgress
    0.48
     perceptual
    0.48
     limitation
    0.47
    POSITIVE LOGITS
    ov
    0.56
    zPosition
    0.47
    rology
    0.47
    VK
    0.46
    NT
    0.46
    ataan
    0.46
    idge
    0.45
    CharAt
    0.45
    DWARF
    0.45
    н
    0.45
    Activations Density 0.000%

    No Known Activations