© 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. 107828
    Prev
    Next
    INDEX
    Explanations

    education, math, science, and business contexts

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

    ease of saying

    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
     NEA
    0.52
     scarc
    0.50
     impersonal
    0.49
     invaluable
    0.48
     affiliate
    0.48
     affiliation
    0.48
    0.47
     at
    0.47
    <%=
    0.45
     pulling
    0.45
    POSITIVE LOGITS
     vVertex
    0.48
     Crime
    0.45
    实验
    0.45
     இலங்க
    0.45
    詃
    0.44
    龕
    0.44
    anova
    0.43
     मुसलमान
    0.43
    pgamma
    0.43
    軛
    0.43
    Activations Density 0.000%

    No Known Activations