© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9465
    Prev
    Next
    INDEX
    Explanations

    error handling and data processing

    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
    <0xF0>
    1.27
    ⁺
    1.20
    🫶
    1.18
    🇯
    1.17
    🇺
    1.15
    +/
    1.15
    🇮
    1.14
    🇫
    1.14
    ⁣
    1.14
    📸
    1.14
    POSITIVE LOGITS
     했다
    1.30
     않았다
    1.29
     Because
    1.23
    했다
    1.14
    Because
    1.11
     않는다
    1.10
     한다
    1.09
     있다
    1.08
     undertake
    1.08
     않고
    1.08
    Activations Density 0.250%

    No Known Activations