© 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. 35681
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons and ranges

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

    equation components, variables, and comparisons

    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
     ribbon
    0.46
     painters
    0.46
     painting
    0.46
     [(
    0.43
     $(
    0.43
     Form
    0.42
     Painting
    0.42
     Ribbon
    0.41
     paint
    0.41
     rid
    0.41
    POSITIVE LOGITS
    HOBBIT
    0.46
     কিশোর
    0.46
    Salman
    0.45
    वारीत
    0.45
    முருக
    0.45
    谘
    0.45
    recomend
    0.44
    muslim
    0.44
    在国内
    0.44
    ابعه
    0.44
    Activations Density 0.000%

    No Known Activations