© 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. 65125
    Prev
    Next
    INDEX
    Explanations

    signing legal documents

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

    signing legal documents

    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
    判定
    0.42
     PHYSI
    0.42
     ጎ
    0.41
     rescu
    0.40
     évaluations
    0.40
     பாதை
    0.40
     لباس
    0.40
     SEASON
    0.38
    喷
    0.38
     perencanaan
    0.38
    POSITIVE LOGITS
     Signing
    1.09
     signing
    1.02
    Signing
    0.98
    signing
    0.95
     signings
    0.85
     signer
    0.84
     podpis
    0.82
    签署
    0.79
    签字
    0.78
    簽
    0.78
    Activations Density 0.088%

    No Known Activations