© 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. 227563
    Prev
    Next
    INDEX
    Explanations

    Civil Liberties Union

    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
     We
    0.54
     Platte
    0.52
     WF
    0.50
    م
    0.49
     컬러
    0.48
     Ashram
    0.48
     아
    0.48
     색
    0.47
     Ats
    0.47
    磵
    0.47
    POSITIVE LOGITS
    めで
    0.48
    uer
    0.46
    ias
    0.45
    ̣
    0.44
    a
    0.43
    ce
    0.43
     ")";
    0.43
    oides
    0.43
    Preview
    0.42
    Several
    0.42
    Activations Density 0.001%

    No Known Activations