© 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. 324
    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
    ,
    2.75
    ،
    2.71
    :
    2.29
    、
    2.26
    /
    1.76
    (
    1.76
    ：
    1.71
    )،
    1.69
    -
    1.65
    ，
    1.64
    POSITIVE LOGITS
     etc
    2.86
     valamint
    2.41
     including
    2.33
     以及
    2.32
    etc
    2.31
     which
    2.23
    尤其是
    2.22
    以及
    2.22
     illetve
    2.20
     특히
    2.19
    Activations Density 4.341%

    No Known Activations