© 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. 40-GEMMASCOPE-2-RES-65K
    7. 2867
    Prev
    Next
    INDEX
    Explanations

    math notes

    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_40_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
    algorith
    0.48
    观测
    0.47
     stvari
    0.47
    ק
    0.47
    יל
    0.45
    贫
    0.44
    棪
    0.44
    魟
    0.44
     miesią
    0.43
     odre
    0.43
    POSITIVE LOGITS
    PPI
    0.57
     P
    0.55
    P
    0.54
    PE
    0.52
     PA
    0.48
    PH
    0.48
    PJ
    0.48
    PN
    0.47
     PN
    0.47
    PA
    0.46
    Activations Density 0.505%

    No Known Activations