© 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. 181940
    Prev
    Next
    INDEX
    Explanations

    Denmark web hosting

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

    know him

    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
    ו
    0.57
    ר
    0.54
    ון
    0.52
    }/\
    0.48
    سل
    0.47
    רות
    0.47
    גה
    0.47
    وجه
    0.46
    ز
    0.45
    酒
    0.45
    POSITIVE LOGITS
     निषे
    0.57
     PlayerSelector
    0.51
     ବି
    0.48
     thoracique
    0.48
    bandSize
    0.47
     Collegiate
    0.47
     Ө
    0.45
     полного
    0.45
     Cambodian
    0.45
     индивидуа
    0.45
    Activations Density 0.000%

    No Known Activations