© 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. 80401
    Prev
    Next
    INDEX
    Explanations

    complied with, playing regular

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

    compatibility with

    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
     pretentious
    0.53
    acağını
    0.49
     kpc
    0.47
    💏
    0.46
     kiya
    0.44
     defineConfig
    0.44
     tabPage
    0.43
     એવી
    0.43
    💋
    0.42
     осо
    0.42
    POSITIVE LOGITS
    allowing
    0.49
    without
    0.46
     även
    0.46
    iss
    0.46
    身体
    0.46
    逐
    0.44
    甚至
    0.44
    abdominal
    0.43
     flows
    0.43
    也可
    0.43
    Activations Density 0.001%

    No Known Activations