© 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. 150372
    Prev
    Next
    INDEX
    Explanations

    eight preschool

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

    flammable dangerous

    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
     Select
    0.52
     แจ
    0.48
     நட்பு
    0.48
    ^{*}}\
    0.48
     Consultation
    0.47
    ærer
    0.47
    .>
    0.46
    棻
    0.46
     със
    0.46
     Traffic
    0.45
    POSITIVE LOGITS
    -
    0.51
    ennies
    0.50
    یل
    0.48
     summarizes
    0.47
     imposes
    0.47
    कर्मा
    0.46
    Sergio
    0.46
     ribosomes
    0.45
    ほん
    0.45
     maximized
    0.45
    Activations Density 0.001%

    No Known Activations