© 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. 109124
    Prev
    Next
    INDEX
    Explanations

    adult male guy

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

    snapshot taken

    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
     haci
    0.57
    丵
    0.51
     држа
    0.50
     daydream
    0.50
    certificado
    0.49
    ईआरटी
    0.49
    UVWXYZ
    0.49
     गाड़ी
    0.48
     যুদ্ধ
    0.48
     harem
    0.48
    POSITIVE LOGITS
     Serving
    0.52
     Painting
    0.49
     So
    0.46
     How
    0.46
     제출
    0.46
    拎
    0.46
     Serialize
    0.46
    upné
    0.45
    。
    0.45
    cribing
    0.44
    Activations Density 0.000%

    No Known Activations