© 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. 153851
    Prev
    Next
    INDEX
    Explanations

    credit history

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

    options ranging

    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
    োক
    0.52
    ы
    0.49
    л
    0.48
    я
    0.48
    ından
    0.47
    ემა
    0.47
    нді
    0.47
    姉
    0.47
    ığı
    0.46
    تهای
    0.46
    POSITIVE LOGITS
     Gh
    0.48
     नमक
    0.48
    SUV
    0.48
    }_{+}
    0.44
     上
    0.44
     منصور
    0.44
     Thar
    0.43
    НИЕ
    0.42
     gh
    0.42
     कुत्ते
    0.42
    Activations Density 0.001%

    No Known Activations