© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45059
    Prev
    Next
    INDEX
    Explanations

    Euclid proved, Einstein showed, extinction, toward second

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    年間
    0.46
    Annual
    0.45
     proliferation
    0.44
    هد
    0.44
    ד
    0.44
    每年
    0.43
    proliferation
    0.42
    Я
    0.42
    YEAR
    0.42
    ELECT
    0.42
    POSITIVE LOGITS
     även
    0.45
    ForSettings
    0.42
     这是
    0.41
     łyż
    0.41
     фонбет
    0.40
     číslo
    0.39
     także
    0.39
    ٣
    0.39
     xrd
    0.39
     QR
    0.39
    Activations Density 0.007%

    No Known Activations