© 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-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 489
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_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
     +
    1.00
     most
    0.99
     (+
    0.97
     resting
    0.91
    :
    0.85
     (+)
    0.85
     duty
    0.81
     mostly
    0.80
     (
    0.80
     “
    0.79
    POSITIVE LOGITS
    usepackage
    2.05
    renewcommand
    1.76
     lembaga
    1.66
    setlength
    1.65
     meghatá
    1.65
    setcounter
    1.64
    newcommand
    1.62
    セット
    1.55
    newtheorem
    1.55
     binatang
    1.51
    Activations Density 0.166%

    No Known Activations