© 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. 43333
    Prev
    Next
    INDEX
    Explanations

    fauna

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

    explaining contexts

    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
    تها
    0.48
    ١
    0.47
    ierte
    0.47
    ക
    0.47
     inklusive
    0.46
     nz
    0.46
    يتها
    0.45
    9
    0.45
    K
    0.45
    WASHINGTON
    0.44
    POSITIVE LOGITS
     внутрен
    0.50
     மருந்த
    0.46
     Vidy
    0.45
     செய்தனர்
    0.44
     प्रतिबंधित
    0.44
     価格
    0.44
     ตำ
    0.44
     Microbiol
    0.43
    <unused2164>
    0.43
     R
    0.43
    Activations Density 0.000%

    No Known Activations