© 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. 36341
    Prev
    Next
    INDEX
    Explanations

    medicinal chemists

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

    future possibilities or explanations

    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
    тың
    0.52
    FOR
    0.49
    rlig
    0.49
    꺼
    0.48
    lamak
    0.48
    мени
    0.48
    i
    0.48
    cfg
    0.47
     귀
    0.47
    שוט
    0.47
    POSITIVE LOGITS
     mutually
    0.43
    क्टर
    0.42
     DR
    0.42
    ációs
    0.42
     ك
    0.41
     “[
    0.41
    在一
    0.41
    قي
    0.41
     verder
    0.40
    進
    0.40
    Activations Density 0.000%

    No Known Activations