© 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. 154830
    Prev
    Next
    INDEX
    Explanations

    shape of credits

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

    listing options

    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
     all
    0.47
     garante
    0.45
    \
    0.43
     IgG
    0.40
     freck
    0.40
     Ireland
    0.40
    0.40
    {
    0.40
     the
    0.39
     Clarks
    0.39
    POSITIVE LOGITS
     previewBuilder
    0.50
    larına
    0.49
     spontaneity
    0.48
     directive
    0.47
    ﺔ
    0.47
     नयी
    0.47
    选项
    0.46
    ándo
    0.46
    惊喜
    0.46
     புதிய
    0.45
    Activations Density 0.003%

    No Known Activations