© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102613
    Prev
    Next
    INDEX
    Explanations

    we're

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \
    -3.20
    {
    -2.41
    In
    -2.30
    艽
    -2.28
    cakup
    -2.25
    Now
    -2.20
    咏
    -2.09
     seperti
    -2.03
    あまり
    -1.99
     như
    -1.98
    POSITIVE LOGITS
    跸
    2.52
     juſt
    2.42
    k
    2.36
     ),
    2.25
    啣
    2.20
    皞
    2.19
    re
    2.14
    2.14
    鲣
    2.06
    珢
    2.03
    Activations Density 0.009%

    No Known Activations