© 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. 240145
    Prev
    Next
    INDEX
    Explanations

    however, free, intact, bulge, location

    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
    女神
    0.47
    WebDriver
    0.46
    🌱
    0.46
     saves
    0.45
     whispers
    0.44
     虽然
    0.44
    有两种
    0.44
    表达式
    0.44
     Signup
    0.43
     editorials
    0.43
    POSITIVE LOGITS
    uran
    0.52
    ній
    0.52
    iligung
    0.51
    няя
    0.49
    itu
    0.49
     н
    0.49
    ικού
    0.48
     mali
    0.48
     keç
    0.48
    мере
    0.46
    Activations Density 0.000%

    No Known Activations