© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 247243
    Prev
    Next
    INDEX
    Explanations

    information processing and quotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ען
    0.47
    .³
    0.46
    .|
    0.46
     barrister
    0.46
    .”[
    0.46
    .”)
    0.45
    gt
    0.45
    .[/
    0.44
    unu
    0.44
     چی
    0.44
    POSITIVE LOGITS
     computeEncoder
    0.57
    因为
    0.48
    一样的
    0.48
    就知道
    0.48
     сотрудни
    0.48
    UpdateTime
    0.48
     inverso
    0.47
     ஒத்து
    0.47
    图像
    0.46
     mascar
    0.46
    Activations Density 0.001%

    No Known Activations