© 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. 96409
    Prev
    Next
    INDEX
    Explanations

    verdicts, unit, risk, competent, many, run, landmark

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

    perform basic steps

    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
    注意的是
    0.48
     connus
    0.46
     totalité
    0.46
     部
    0.45
    外界
    0.45
     miles
    0.43
     NSLog
    0.42
     websocket
    0.42
     postseason
    0.41
     nieco
    0.41
    POSITIVE LOGITS
    kamer
    0.54
    Pyrazole
    0.51
    rym
    0.49
    䂘
    0.49
    й
    0.48
    觫
    0.48
    zm
    0.47
    kish
    0.46
    fut
    0.46
    кий
    0.46
    Activations Density 0.000%

    No Known Activations