© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1582
    Prev
    Next
    INDEX
    Explanations

    special characters before descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    0.65
    !
    0.58
     [
    0.58
     *
    0.57
    ba
    0.57
     azul
    0.54
    *
    0.50
     восем
    0.50
     verdad
    0.47
     I
    0.46
    POSITIVE LOGITS
    Provides
    1.07
    Providing
    1.07
    Provide
    1.04
    Creates
    1.02
     Provides
    0.98
     Providing
    0.96
     Enables
    0.96
    致力于
    0.93
     Provide
    0.92
     위한
    0.91
    Activations Density 3.278%

    No Known Activations