© 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. 237718
    Prev
    Next
    INDEX
    Explanations

    money, numeric, schools, ways, series

    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
     ی
    0.48
    BR
    0.47
    eka
    0.46
    KU
    0.46
    Meu
    0.45
     autobiography
    0.45
    GO
    0.45
    𝗝
    0.44
     اول
    0.44
    pm
    0.44
    POSITIVE LOGITS
    льность
    0.46
     избе
    0.45
     diferencial
    0.45
    eOut
    0.44
    stylers
    0.44
    مارسة
    0.44
    antera
    0.43
     femenina
    0.43
    imbangan
    0.43
     имена
    0.43
    Activations Density 0.001%

    No Known Activations