© 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. 199887
    Prev
    Next
    INDEX
    Explanations

    Install libraries

    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
    ла
    0.52
    ᒃ
    0.49
     природе
    0.47
    ван
    0.46
     đối
    0.46
     бір
    0.46
     красо
    0.45
     facilmente
    0.44
    ологи
    0.43
    सह
    0.43
    POSITIVE LOGITS
    in
    0.49
     to
    0.48
     Orders
    0.48
     Sales
    0.47
     orders
    0.46
     A
    0.45
    ag
    0.45
    ess
    0.45
    otta
    0.45
    orders
    0.44
    Activations Density 0.004%

    No Known Activations