© 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. 22-GEMMASCOPE-2-RES-16K
    7. 497
    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_22_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
     foreign
    0.81
     well
    0.79
     Foreign
    0.78
     Tagen
    0.78
     possibly
    0.76
    즈
    0.75
     če
    0.75
    拔
    0.74
     turn
    0.71
     cent
    0.71
    POSITIVE LOGITS
    ynthia
    1.45
    radle
    1.43
    ategor
    1.40
    anceled
    1.36
    unningham
    1.36
    uckoo
    1.33
    emetery
    1.32
    autions
    1.31
    ULTURE
    1.29
    rescent
    1.28
    Activations Density 0.587%

    No Known Activations