© 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. 71659
    Prev
    Next
    INDEX
    Explanations

    safety and medicine

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

    shift, scans, change, encodes, mix

    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
    전에
    0.44
    áže
    0.43
    Là
    0.43
    ă
    0.42
    ครบ
    0.42
    전
    0.41
    irc
    0.41
    大家都
    0.41
    ą
    0.41
    il
    0.40
    POSITIVE LOGITS
     نسبت
    0.52
    oucault
    0.47
     وجود
    0.47
    examine
    0.47
     اُن
    0.47
     Information
    0.46
    information
    0.46
    evaluation
    0.46
    บวน
    0.46
    opinion
    0.45
    Activations Density 0.001%

    No Known Activations