© 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. 219092
    Prev
    Next
    INDEX
    Explanations

    business and industry

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

    numbers and sequences

    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
     LOCAL
    0.43
     locais
    0.43
    ☁
    0.42
     ভাইকে
    0.42
     bequeathed
    0.42
     SOURCES
    0.40
     venced
    0.40
    Tay
    0.40
    সম্যান
    0.40
     recruits
    0.39
    POSITIVE LOGITS
    相談
    0.48
    轭
    0.47
    立場
    0.47
    鶚
    0.44
    ValMap
    0.43
    વેશ
    0.43
     aank
    0.42
    Daten
    0.42
     polynom
    0.42
    幟
    0.42
    Activations Density 0.000%

    No Known Activations