© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 15701
    Prev
    Next
    INDEX
    Explanations

    work and company details

    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
    dinger
    0.47
     clasific
    0.39
     bioge
    0.39
     Keaton
    0.39
     graciously
    0.38
     mistura
    0.38
     sierp
    0.38
    蛹
    0.38
     gero
    0.38
     Asheville
    0.38
    POSITIVE LOGITS
     근무
    0.75
    公司
    0.71
     karyawan
    0.71
     업무
    0.71
     ಕೆಲಸ
    0.70
     회사
    0.70
     ജോലി
    0.68
     perusahaan
    0.68
     કંપની
    0.67
     bekerja
    0.65
    Activations Density 0.007%

    No Known Activations