© 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. 116268
    Prev
    Next
    INDEX
    Explanations

    strange cat poop

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

    creating new features or powers

    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
    著者
    0.52
    炰
    0.51
    几天
    0.51
     Hôtel
    0.50
    𝑨
    0.49
    Appellant
    0.48
     Badal
    0.48
    Decedent
    0.48
    🏩
    0.47
    वृ
    0.47
    POSITIVE LOGITS
     '
    0.51
    to
    0.48
     -
    0.47
    ly
    0.47
     gu
    0.45
    &
    0.45
     խ
    0.45
    io
    0.44
     unsaturated
    0.44
    light
    0.43
    Activations Density 0.000%

    No Known Activations