© 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. 188642
    Prev
    Next
    INDEX
    Explanations

    properties, races, countries

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

    cut off

    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
    '
    0.61
     computable
    0.50
     professionalism
    0.45
    фессиона
    0.44
     minimum
    0.43
     Well
    0.43
    номер
    0.43
     Bliss
    0.42
     pH
    0.40
     preoccupation
    0.40
    POSITIVE LOGITS
     সপ্ত
    0.52
    withtag
    0.52
     プラ
    0.51
    棗
    0.50
    鶘
    0.50
     olok
    0.49
     Göttingen
    0.49
     生産
    0.48
    
    0.48
    ্টো
    0.48
    Activations Density 0.000%

    No Known Activations