Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 19397
    Prev
    Next
    INDEX
    Explanations

    full

    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
     termasuk
    0.40
     évén
    0.39
    裱
    0.39
    睜
    0.39
     gồm
    0.38
    स्तरीय
    0.37
     !!!!
    0.37
     بلکہ
    0.37
     včetně
    0.37
     {{-
    0.36
    POSITIVE LOGITS
     Full
    0.72
    Full
    0.66
    FULL
    0.59
     Fuller
    0.58
     fuller
    0.57
    full
    0.55
     FULL
    0.54
     полно
    0.54
     full
    0.51
    getFull
    0.51
    Activations Density 0.007%

    No Known Activations