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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 4537
    Prev
    Next
    INDEX
    Explanations

    steps, analysis, exceptions, thinking

    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
     (
    0.53
    0.50
     een
    0.46
     via
    0.45
     in
    0.42
     through
    0.41
     [
    0.41
     -
    0.41
     \
    0.39
     during
    0.38
    POSITIVE LOGITS
    ，
    0.73
    。
    0.68
    而且
    0.68
    也
    0.66
    也是
    0.66
    并且
    0.65
    。<
    0.64
    。”
    0.63
    。"
    0.62
    也不
    0.62
    Activations Density 0.079%

    No Known Activations