© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 1382
    Prev
    Next
    INDEX
    Explanations

    code comments and examples

    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
    <strong>
    0.97
    <em>
    0.84
    <b>
    0.80
    <sup>
    0.80
    embrance
    0.69
    imeters
    0.67
    <code>
    0.67
    <i>
    0.64
     meg
    0.64
    <start_of_image>
    0.64
    POSITIVE LOGITS
     Also
    1.41
     Note
    1.37
     This
    1.32
    This
    1.31
    Also
    1.28
    ================
    1.27
    Note
    1.27
     NOTE
    1.27
     Additionally
    1.26
     Furthermore
    1.23
    Activations Density 0.066%

    No Known Activations