© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11629
    Prev
    Next
    INDEX
    Explanations

    logging output

    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_40_width_16k_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
    console
    0.47
    ("%
    0.43
     f
    0.42
     `${
    0.42
    Fprintf
    0.42
    ("{}
    0.41
     conso
    0.39
    `${
    0.39
    fprintf
    0.38
     []
    0.38
    POSITIVE LOGITS
    畋
    0.48
    <unused722>
    0.44
    нях
    0.44
    رة
    0.42
    MIT
    0.41
    Cited
    0.40
     TECH
    0.40
    潛行
    0.40
    HYDRO
    0.40
    TRUST
    0.39
    Activations Density 0.080%

    No Known Activations