© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 20732
    Prev
    Next
    INDEX
    Explanations

    shared libraries (.so)

    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
     выбора
    0.43
     weeks
    0.43
     Zhou
    0.42
    周
    0.41
     choice
    0.38
    Previews
    0.38
     Play
    0.37
     Dreams
    0.37
     whistling
    0.37
    忉
    0.37
    POSITIVE LOGITS
    Bundle
    0.74
     Bundle
    0.66
     bundle
    0.65
    bundle
    0.63
     OS
    0.62
     bundles
    0.61
    BUND
    0.57
     Bund
    0.56
     os
    0.56
    Bund
    0.54
    Activations Density 0.002%

    No Known Activations