© 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. 86449
    Prev
    Next
    INDEX
    Explanations

    McCann

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

    events and incidents

    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
    ℞
    0.49
    人在
    0.47
    ўцаў
    0.43
     новую
    0.42
    斑
    0.42
    ())),
    0.42
    ⇰
    0.42
     도움
    0.42
    σή
    0.41
    馏
    0.41
    POSITIVE LOGITS
     impres
    0.49
     evita
    0.48
     h
    0.48
     prezident
    0.47
     rea
    0.47
     politika
    0.47
    laki
    0.46
     raz
    0.46
     zel
    0.46
     hama
    0.46
    Activations Density 0.001%

    No Known Activations