© 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. 123850
    Prev
    Next
    INDEX
    Explanations

    offering specialized programs or services

    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
    不
    0.50
    Meu
    0.47
    掉
    0.46
    Lay
    0.45
    ี้ย
    0.44
     روی
    0.44
     مریض
    0.44
     값을
    0.43
    G
    0.43
    ()]
    0.43
    POSITIVE LOGITS
     repetitions
    0.47
    льников
    0.46
     Olive
    0.46
     markets
    0.45
     almond
    0.44
     Yakima
    0.44
     Orange
    0.44
    markets
    0.44
     Jabal
    0.44
     само
    0.43
    Activations Density 0.001%

    No Known Activations