© 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. 31-GEMMASCOPE-2-RES-262K
    7. 25328
    Prev
    Next
    INDEX
    Explanations

    comparison phrases

    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_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
    ren
    0.46
    üllt
    0.43
    rents
    0.42
    sten
    0.40
     paging
    0.38
    جان
    0.38
    ứng
    0.38
    l
    0.38
    p
    0.37
     أنا
    0.37
    POSITIVE LOGITS
    btnPrint
    0.50
    PerTrial
    0.48
    InSection
    0.48
    SetStr
    0.45
     ы
    0.45
     Warzone
    0.45
     mohabbat
    0.44
     будет
    0.43
    MAPb
    0.43
     सुधा
    0.43
    Activations Density 0.006%

    No Known Activations