© 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. 148262
    Prev
    Next
    INDEX
    Explanations

    Civil tape private dynamic

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

    example word

    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
    ремя
    0.54
    રમ
    0.52
     📫
    0.51
    的分
    0.51
     Configur
    0.51
     显示
    0.50
     标准
    0.49
     情况
    0.48
    分为
    0.48
     Corrosion
    0.48
    POSITIVE LOGITS
     office
    0.50
    K
    0.47
     commission
    0.46
     object
    0.45
     lubricant
    0.45
     resignation
    0.45
     solicitor
    0.44
     bal
    0.44
    F
    0.43
     ministry
    0.43
    Activations Density 0.000%

    No Known Activations