© 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. 123053
    Prev
    Next
    INDEX
    Explanations

    expertise and reconstruction

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

    plague many, littered with examples

    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
    EP
    0.48
    मा
    0.45
    ד
    0.45
    有点
    0.44
    ン
    0.43
    AE
    0.43
    슬
    0.43
     ਜਾ
    0.42
    が出
    0.42
    EO
    0.42
    POSITIVE LOGITS
     bolesti
    0.47
     début
    0.46
     технологии
    0.45
     pursued
    0.44
     koron
    0.43
     సార
    0.43
    тности
    0.43
     wavefront
    0.43
     pipette
    0.43
     vidé
    0.42
    Activations Density 0.000%

    No Known Activations