Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 2177
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming

    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_29_width_65k_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
     explained
    0.71
     concept
    0.71
     rest
    0.65
     communique
    0.65
     cdot
    0.64
     sub
    0.63
     hurting
    0.62
     *}(
    0.62
     persistent
    0.61
     formula
    0.60
    POSITIVE LOGITS
    ```
    1.61
     ```
    1.15
    <code>
    0.97
    sudo
    0.93
    ``
    0.89
    Output
    0.88
    $$\
    0.86
    python
    0.84
    [
    0.81
    output
    0.81
    Activations Density 0.582%

    No Known Activations