© 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. 41-GEMMASCOPE-2-RES-262K
    7. 5385
    Prev
    Next
    INDEX
    Explanations

    jurisdiction

    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_all/layer_41_width_262k_l0_big
    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
    њи
    0.42
    企業
    0.41
     demonstrators
    0.41
     hoti
    0.40
    tel
    0.40
     ប
    0.39
    בי
    0.38
    玻璃
    0.37
     Westminster
    0.37
     teljes
    0.37
    POSITIVE LOGITS
     harsh
    0.45
     LIGO
    0.43
     grim
    0.39
    Quite
    0.39
     hars
    0.39
    出して
    0.39
    出す
    0.39
     meaning
    0.38
     listOf
    0.38
     приобрести
    0.38
    Activations Density 0.000%

    No Known Activations