© 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. 17-GEMMASCOPE-2-RES-16K
    7. 215
    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
    ,
    1.19
     for
    1.14
     to
    1.13
     will
    1.12
     on
    1.09
     can
    1.05
     civil
    1.03
     be
    1.03
     ’
    1.02
     ran
    1.02
    POSITIVE LOGITS
    tex
    1.88
    unità
    1.60
    Zitat
    1.59
    asci
    1.55
    Fuente
    1.51
    hình
    1.50
    ánk
    1.49
    italic
    1.48
    מבר
    1.47
    ካል
    1.47
    Activations Density 0.417%

    No Known Activations