© 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. 37708
    Prev
    Next
    INDEX
    Explanations

    wrongdoing or consequences

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

    categorized by

    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
     (
    0.54
    的情况下
    0.45
     对于
    0.45
    ing
    0.45
     of
    0.43
     *
    0.43
    !
    0.43
     War
    0.43
    กรณี
    0.42
    uri
    0.42
    POSITIVE LOGITS
     aplatis
    0.45
    分かる
    0.43
    traces
    0.42
    ੳ
    0.41
    わかる
    0.40
     anciennes
    0.40
     antigos
    0.40
     rotates
    0.40
    selectTable
    0.40
     mensuales
    0.40
    Activations Density 0.000%

    No Known Activations