© 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. 121548
    Prev
    Next
    INDEX
    Explanations

    services, discrete, agent, lemongrass

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

    loop runs repeatedly

    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
    gal
    0.55
    R
    0.54
     maior
    0.50
     gal
    0.49
    G
    0.48
    A
    0.48
    cover
    0.47
    path
    0.46
    m
    0.45
    E
    0.45
    POSITIVE LOGITS
     торговли
    0.54
    слары
    0.50
    க்கத்தில்
    0.50
     государство
    0.49
     обязанности
    0.49
     Mudah
    0.48
    к
    0.48
    орк
    0.47
     зав
    0.47
    owanych
    0.47
    Activations Density 0.000%

    No Known Activations