© 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. 59741
    Prev
    Next
    INDEX
    Explanations

    data structures and code snippets

    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
     our
    -1.64
    その他の
    -1.62
    鲧
    -1.55
    hehehe
    -1.47
     généralement
    -1.41
     množství
    -1.40
    behaved
    -1.39
    eronau
    -1.38
     fréquemment
    -1.38
     noires
    -1.37
    POSITIVE LOGITS
     is
    2.11
     in
    1.78
     its
    1.66
     it
    1.55
     with
    1.51
    它的
    1.41
    ‌.
    1.33
    thâu
    1.31
     его
    1.28
    ném
    1.25
    Activations Density 0.022%

    No Known Activations