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-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2234
    Prev
    Next
    INDEX
    Explanations

    JSON objects and markup tags

    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_17_width_16k_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
     [
    0.77
     Even
    0.76
     •
    0.75
     (
    0.72
     set
    0.72
     (~
    0.72
     …
    0.70
     ~
    0.70
     (\
    0.69
     *
    0.69
    POSITIVE LOGITS
     Beruf
    0.83
     வருவத
    0.83
    ünü
    0.82
     potentialities
    0.82
     virtud
    0.81
    ۪
    0.79
    intai
    0.78
     सलामी
    0.78
     institution
    0.78
    
    0.78
    Activations Density 0.387%

    No Known Activations