© 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. 74467
    Prev
    Next
    INDEX
    Explanations

    exceptions and permissions

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

    damages unless acted

    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
     Prospective
    0.49
     prospective
    0.48
    0.44
    t
    0.42
     Mar
    0.41
     T
    0.41
     Like
    0.38
     Performance
    0.38
     Perform
    0.38
     a
    0.38
    POSITIVE LOGITS
     إلا
    0.53
     Ausnahme
    0.47
     kecuali
    0.46
     നമഃ
    0.46
    除非
    0.46
    ၆
    0.45
     EXCEPT
    0.45
    зи
    0.45
    सीएल
    0.45
    俱
    0.45
    Activations Density 0.007%

    No Known Activations