© 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. 85985
    Prev
    Next
    INDEX
    Explanations

    liability and responsibility

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

    processor family

    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
    ProductRunnable
    0.50
    桝
    0.50
    贤
    0.48
     исследова
    0.48
     impuestos
    0.47
    テキスト
    0.46
    Pract
    0.46
     pract
    0.45
    Texto
    0.45
    বো
    0.45
    POSITIVE LOGITS
    lio
    0.52
     unavailable
    0.51
     deleting
    0.46
    tz
    0.43
    u
    0.43
     special
    0.43
     nont
    0.43
    line
    0.42
    olen
    0.42
    tiny
    0.42
    Activations Density 0.001%

    No Known Activations