© 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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 19270
    Prev
    Next
    INDEX
    Explanations

    code blocks and technical output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metac
    0.73
    }\}$.
    0.72
    ◅
    0.72
    ();//
    0.72
    ំពោះ
    0.71
    orate
    0.71
    そもそも
    0.69
     तलब
    0.68
    。",
    0.68
     lastname
    0.67
    POSITIVE LOGITS
    ```
    1.46
     ```
    1.26
    $$\
    1.11
    \[
    1.08
    $$
    1.07
     $$\
    0.99
     $$
    0.99
    <code>
    0.88
    <blockquote>
    0.86
    <start_of_image>
    0.85
    Activations Density 0.271%

    No Known Activations