© 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. 197991
    Prev
    Next
    INDEX
    Explanations

    money and quantitative traits

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

    grey-silver foliage; party-opponent; Foundation Versions; Molecule Inhibitors

    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
    DIC
    0.48
    𝚜
    0.48
     kir
    0.47
     キ
    0.46
    ALCHEMY
    0.45
     Kiss
    0.45
     کلی
    0.44
     韓国
    0.44
     KIR
    0.44
     추출
    0.44
    POSITIVE LOGITS
    渐渐
    0.53
    钱
    0.45
    ा
    0.44
    其
    0.44
    体会
    0.44
    continuous
    0.44
     foodstuffs
    0.44
    逐渐
    0.43
    良好
    0.42
    जेदार
    0.41
    Activations Density 0.000%

    No Known Activations