© 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. 179108
    Prev
    Next
    INDEX
    Explanations

    paper proposes

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

    non-existent animal, white, restriction

    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
     Esp
    0.49
    Meine
    0.49
     Mays
    0.45
     bords
    0.43
     öffentliche
    0.43
     Meine
    0.42
    <unused612>
    0.42
     sombras
    0.42
     받아
    0.41
     täglich
    0.41
    POSITIVE LOGITS
     manipulate
    0.50
    ğini
    0.45
     என்பவர்
    0.43
    
    0.42
    Lucene
    0.42
     Burnu
    0.42
     investigate
    0.41
    โก
    0.41
     fic
    0.41
    的服务
    0.41
    Activations Density 0.001%

    No Known Activations