© 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. 61573
    Prev
    Next
    INDEX
    Explanations

    extremely special

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

    keywords related to job roles

    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
     ಸ್ಟ
    0.46
     பச
    0.44
    гре
    0.43
    јединачна
    0.43
     ಎರ
    0.42
    Ⲃ
    0.42
     ветер
    0.42
    氯
    0.42
     باد
    0.42
     tiêu
    0.41
    POSITIVE LOGITS
     Perp
    0.51
    เรา
    0.47
    numerator
    0.46
    __)
    0.45
     \|
    0.43
    \")
    0.43
    र्टी
    0.43
    __/
    0.43
     Departamento
    0.43
    Você
    0.42
    Activations Density 0.000%

    No Known Activations