© 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. 150719
    Prev
    Next
    INDEX
    Explanations

    charter destination, Milan directed, expert advice

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

    lists of numbers

    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
     bukti
    0.52
     piety
    0.51
     lek
    0.49
     vra
    0.48
    鐵
    0.47
     identifik
    0.47
     lepid
    0.47
     persamaan
    0.47
    雞
    0.47
    萩
    0.46
    POSITIVE LOGITS
    ርስዎ
    0.45
    Regions
    0.43
     solution
    0.42
    处于
    0.41
     airborne
    0.41
     Course
    0.40
     Solution
    0.40
    arctan
    0.40
    将会
    0.40
    zetac
    0.40
    Activations Density 0.001%

    No Known Activations