© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 171
    Prev
    Next
    INDEX
    Explanations

    links to find help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eter
    0.50
    :
    0.47
    hender
    0.46
    0.45
    <strong>
    0.43
    erent
    0.43
    acity
    0.42
      
    0.41
     (
    0.41
     Eastern
    0.41
    POSITIVE LOGITS
     satış
    0.98
    MovieModal
    0.95
     keamanan
    0.95
    Callories
    0.92
    दिग्ध
    0.92
    ϡ
    0.91
     malzem
    0.91
     pertandingan
    0.91
    Seqlist
    0.90
     livros
    0.89
    Activations Density 0.082%

    No Known Activations