© 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. 567
    Prev
    Next
    INDEX
    Explanations

    roman numeral II

    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
    <eos>
    1.95
    <unused60>
    1.23
     \"
    1.22
     […]
    1.21
     \\
    1.21
    <start_of_image>
    1.18
    .");
    1.12
     ...");
    1.11
     {}".
    1.09
     none
    1.09
    POSITIVE LOGITS
    <u>
    1.71
    Nota
    1.54
    Highlights
    1.48
    Baca
    1.46
    Ré
    1.46
    Conclusion
    1.44
    RELATED
    1.43
    FOR
    1.43
    NOTE
    1.42
    MUST
    1.41
    Activations Density 0.029%

    No Known Activations