© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66016
    Prev
    Next
    INDEX
    Explanations

    locally advanced

    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
    farer
    -1.52
    available
    -1.51
    oused
    -1.49
    Mål
    -1.39
     ー
    -1.37
    payers
    -1.36
    점
    -1.35
    return
    -1.34
     rè
    -1.33
    wrights
    -1.31
    POSITIVE LOGITS
     only
    2.38
     though
    2.34
     with
    2.34
     whose
    2.09
     while
    2.03
     from
    2.03
     their
    2.00
     those
    2.00
     who
    1.86
     although
    1.86
    Activations Density 0.096%

    No Known Activations