© 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. 12957
    Prev
    Next
    INDEX
    Explanations

    program files paths

    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
    Sometimes
    -1.31
    譎
    -1.23
     wirklich
    -1.23
     Tudo
    -1.20
    They
    -1.14
     complementar
    -1.13
     lanz
    -1.13
    Tentang
    -1.11
    HexString
    -1.10
    ateľ
    -1.10
    POSITIVE LOGITS
     it
    1.62
     of
    1.41
    2
    1.22
     предме
    1.12
     Затем
    1.11
    (
    1.09
     folgende
    1.08
     you
    1.05
     '
    1.05
    ://
    1.04
    Activations Density 0.089%

    No Known Activations