© 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-65K
    7. 4798
    Prev
    Next
    INDEX
    Explanations

    exponential math and code

    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_65k_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
    ３
    0.50
    রি
    0.49
    Bsky
    0.47
    DeleteDialogOpen
    0.46
    เร็ว
    0.46
     ሶ
    0.45
    删除
    0.44
    éroport
    0.44
    𝟑
    0.44
    DATABASE
    0.44
    POSITIVE LOGITS
     eines
    0.49
     Escherichia
    0.47
     einer
    0.47
     Esquire
    0.46
     Generalized
    0.46
     Exhibit
    0.45
     Explained
    0.45
     koncept
    0.45
     arguably
    0.45
     Nursing
    0.45
    Activations Density 0.078%

    No Known Activations