© 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. 40-GEMMASCOPE-2-RES-262K
    7. 9444
    Prev
    Next
    INDEX
    Explanations

    names by parts

    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_40_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
     softmax
    0.44
     piecewise
    0.42
     interoper
    0.41
    樋
    0.39
     อื่น
    0.39
     preprocessing
    0.38
     trigonometric
    0.38
     conjugacy
    0.38
     Percolation
    0.38
     ẞ
    0.38
    POSITIVE LOGITS
    ira
    0.52
    ara
    0.50
    ata
    0.50
    ana
    0.47
    ari
    0.46
    apa
    0.45
    uka
    0.44
    una
    0.44
    que
    0.44
    aga
    0.44
    Activations Density 0.003%

    No Known Activations