© 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. 47084
    Prev
    Next
    INDEX
    Explanations

    adopted for adoption

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

    multi-language words

    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
    getSupported
    0.46
    নো
    0.45
    ন্ধে
    0.45
     development
    0.44
     smartest
    0.44
    🇸
    0.44
    ロ
    0.43
    開発
    0.43
     Deutschland
    0.43
    jd
    0.42
    POSITIVE LOGITS
     swells
    0.52
     Mục
    0.50
    ிருந்த
    0.49
    的时候
    0.47
     புற
    0.47
    钵
    0.47
    चा
    0.46
     〈
    0.46
     திருப்பி
    0.46
     бара
    0.46
    Activations Density 0.000%

    No Known Activations