© 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. 36985
    Prev
    Next
    INDEX
    Explanations

    relief, if you

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

    image as input

    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
    уре
    0.50
     রাস্তায়
    0.47
    篪
    0.47
    ע
    0.47
     ডিসেম্বর
    0.46
    ש
    0.46
    يي
    0.44
    ן
    0.43
    ウル
    0.43
    分解
    0.43
    POSITIVE LOGITS
     alfalfa
    0.49
     phyl
    0.48
    ಗಳಿವೆ
    0.48
     veremos
    0.48
     adjuvant
    0.47
     diverses
    0.47
     asphalt
    0.46
     radiographic
    0.46
    thro
    0.46
     sponges
    0.46
    Activations Density 0.000%

    No Known Activations