© 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. 50469
    Prev
    Next
    INDEX
    Explanations

    edge and contour detection

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

    contour approximation

    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
    嬂
    0.45
     ကြ
    0.44
    콥
    0.44
    ʢ
    0.43
     የቀ
    0.43
     служба
    0.43
    โฟ
    0.41
     جلو
    0.41
    妫
    0.41
    郓
    0.40
    POSITIVE LOGITS
    cout
    0.43
     islands
    0.42
     hydrology
    0.42
     scaffold
    0.41
     amph
    0.40
    getJSON
    0.40
     geometry
    0.40
     monaster
    0.40
     dungeons
    0.40
     context
    0.39
    Activations Density 0.000%

    No Known Activations