© 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. 34821
    Prev
    Next
    INDEX
    Explanations

    lists and examples

    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
     需要
    0.41
    క్షణ
    0.39
    Gets
    0.38
    开始
    0.37
    灵活
    0.37
    SSON
    0.37
    诱
    0.36
    ℕ
    0.36
    getSupported
    0.36
    ՛
    0.35
    POSITIVE LOGITS
     tutur
    0.42
     tutte
    0.42
     rupee
    0.41
     malnourished
    0.40
    सुम
    0.40
    画像の
    0.40
     testicular
    0.39
     freck
    0.39
    その他
    0.39
     wszystkie
    0.39
    Activations Density 0.012%

    No Known Activations