© 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. 30328
    Prev
    Next
    INDEX
    Explanations

    file paths and project structures

    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
    uis
    0.42
     কেউ
    0.40
    。...
    0.38
    ču
    0.38
    aisen
    0.37
     collectively
    0.37
    俺
    0.37
     FileManager
    0.37
     کاروب
    0.37
    ėtų
    0.36
    POSITIVE LOGITS
     Staffel
    0.39
    താണ്
    0.38
     SRC
    0.38
    ඨ
    0.37
     Beispiele
    0.37
    EXAMPLES
    0.37
     erstes
    0.37
    src
    0.36
     Zahlen
    0.36
    Kons
    0.36
    Activations Density 0.015%

    No Known Activations