© 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. 132632
    Prev
    Next
    INDEX
    Explanations

    grades 'A'

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

    automation & job loss

    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
     uncertainty
    0.45
     Ирина
    0.43
     김
    0.42
     홍
    0.42
     یقینی
    0.42
    ের
    0.42
     bangs
    0.42
     예상
    0.42
    낯
    0.42
    김
    0.41
    POSITIVE LOGITS
    DataXYZ
    0.51
    IsResolver
    0.46
     científicos
    0.45
    AnalyzeAction
    0.45
    ICreate
    0.44
    كُمْ
    0.44
    ijd
    0.43
    ="..."
    0.43
    ibar
    0.43
    AutoGen
    0.43
    Activations Density 0.002%

    No Known Activations