© 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. 68791
    Prev
    Next
    INDEX
    Explanations

    business and daily operations

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

    formal definitions and actions

    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
     overseen
    0.54
    厄
    0.46
     stormed
    0.44
     encompassed
    0.44
    ก
    0.44
    ωνα
    0.43
     apprehended
    0.43
    ிக்க
    0.42
     inward
    0.41
    傛
    0.41
    POSITIVE LOGITS
     程序
    0.52
     Soci
    0.49
     設定
    0.48
     Nahrung
    0.48
     まず
    0.47
     Bagan
    0.47
     Bif
    0.47
     Consult
    0.46
     Consultation
    0.46
     Balashov
    0.46
    Activations Density 0.001%

    No Known Activations