© 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. 132630
    Prev
    Next
    INDEX
    Explanations

    proposals over, run a

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

    mine threat

    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
     City
    0.53
    u
    0.53
    </h2>
    0.52
     County
    0.51
     Entry
    0.50
    </h3>
    0.50
    </b>
    0.50
     city
    0.49
     F
    0.49
     gym
    0.49
    POSITIVE LOGITS
    இந்த
    0.53
    횽
    0.52
    ПУ
    0.50
    之前的
    0.48
    tìm
    0.48
    ностями
    0.47
    BACH
    0.46
    SLOW
    0.46
    스를
    0.46
    눗
    0.46
    Activations Density 0.000%

    No Known Activations