© 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. 34021
    Prev
    Next
    INDEX
    Explanations

    travelling

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

    glucose oxidase test

    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
     shirtless
    0.48
     tangy
    0.47
    times
    0.46
    it
    0.46
     unatt
    0.45
    q
    0.45
     idk
    0.44
    pq
    0.44
     dystopian
    0.44
     wept
    0.43
    POSITIVE LOGITS
     толькі
    0.54
     sequentially
    0.51
     выход
    0.47
    К
    0.47
     лише
    0.46
    ைகள்
    0.45
    ніка
    0.45
     известный
    0.45
    йдз
    0.44
     procédures
    0.43
    Activations Density 0.001%

    No Known Activations