© 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. 22-GEMMASCOPE-2-RES-16K
    4. 128
    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
    ],”
    0.80
     ger
    0.77
     cul
    0.73
    ၤ
    0.72
     revisited
    0.72
    ]-
    0.72
     witnessed
    0.72
     ප්ර
    0.71
     incorporated
    0.71
    .]
    0.70
    POSITIVE LOGITS
    (
    3.04
    ((
    2.67
    ("
    2.60
    ('
    2.49
    (_
    2.47
    ([
    2.46
    ()
    2.39
    (-
    2.38
    (
    2.37
    (/*
    2.36
    Activations Density 0.615%

    No Known Activations