© 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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 141099
    Prev
    Next
    INDEX
    Explanations

    Augustus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
     a
    0.59
    {
    0.55
    ູບ
    0.53
     capability
    0.51
    /=
    0.50
    【
    0.49
    $'
    0.49
    पणे
    0.48
    果
    0.47
    EST
    0.47
    POSITIVE LOGITS
     टिश्यू
    0.54
    ни
    0.53
     Cerebral
    0.53
    ۔
    0.52
     Andover
    0.48
    <unused414>
    0.46
    uckland
    0.46
     Oxide
    0.46
    ifier
    0.46
     Donations
    0.46
    Activations Density 0.000%

    No Known Activations