© 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. 26944
    Prev
    Next
    INDEX
    Explanations

    legal and medical agreements

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

    Data, Education, Focus, Consent, Artifact

    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
    抉
    0.58
    眄
    0.53
    嗤
    0.50
    Какой
    0.49
    ाइ
    0.49
    语
    0.48
    갛
    0.48
    납
    0.48
    喟
    0.48
    푞
    0.47
    POSITIVE LOGITS
     parentheses
    0.54
     periodic
    0.53
     Stokes
    0.52
     wetting
    0.52
     punctuated
    0.52
     bur
    0.50
     northbound
    0.50
     NI
    0.49
     signaling
    0.48
     septembre
    0.48
    Activations Density 0.000%

    No Known Activations