© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167382
    Prev
    Next
    INDEX
    Explanations

    component integration

    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_262k_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
     manzanas
    0.40
    䢂
    0.40
    ليز
    0.40
     kõik
    0.39
    ಳ್ಳ
    0.39
     مربع
    0.38
    routerProps
    0.38
     hoteles
    0.38
     fillColorSpace
    0.38
    цька
    0.37
    POSITIVE LOGITS
    Self
    0.38
    level
    0.36
    unit
    0.36
     Self
    0.36
    veer
    0.35
     이제
    0.35
    ỳ
    0.35
    atten
    0.34
     अब
    0.34
    vir
    0.34
    Activations Density 0.000%

    No Known Activations