© 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. 974
    Prev
    Next
    INDEX
    Explanations

    our liability or possessions

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

    output redirection

    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
    d
    0.50
    ela
    0.49
    zine
    0.49
    DS
    0.48
    h
    0.48
    ด
    0.47
    Serve
    0.47
    瞎
    0.46
    egg
    0.45
    ucked
    0.45
    POSITIVE LOGITS
    年に
    0.55
     tới
    0.48
    стых
    0.47
    第一个
    0.46
     contribution
    0.46
     posiblemente
    0.46
    ्यांना
    0.46
    ніх
    0.45
     ersten
    0.45
     Contributions
    0.45
    Activations Density 0.001%

    No Known Activations