© 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. 238074
    Prev
    Next
    INDEX
    Explanations

    settings, brochure, days, lining, leg, variety, of

    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
    InCategory
    0.45
     النار
    0.44
    }}-\
    0.43
     objectionable
    0.42
     clinging
    0.42
    籹
    0.42
     Lí
    0.42
    也會
    0.42
    க்கூ
    0.41
    }^{+}
    0.41
    POSITIVE LOGITS
     уйна
    0.61
     хоккей
    0.48
     ры
    0.47
    pti
    0.46
     профессиона
    0.46
     ключе
    0.44
     реализова
    0.44
     мире
    0.43
     кро
    0.43
     खेळ
    0.43
    Activations Density 0.000%

    No Known Activations