© 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. 454
    Prev
    Next
    INDEX
    Explanations

    internet domain extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    "
    1.59
    .
    1.50
    ...
    1.44
    (
    1.37
    .+
    1.33
    /
    1.32
    :
    1.29
    ”
    1.24
    …
    1.20
    -
    1.14
    POSITIVE LOGITS
    jpg
    2.46
    ᐟ
    2.17
    png
    2.11
    indd
    2.05
    JPG
    2.04
    com
    2.04
    htm
    1.98
    org
    1.95
    aspx
    1.94
    gov
    1.86
    Activations Density 2.151%

    No Known Activations