© 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. 15044
    Prev
    Next
    INDEX
    Explanations

    Edo, hepatic, beta, Miranda

    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
    Ꝑ
    -2.41
    茕
    -2.39
    ↑↑↑</
    -2.22
    镡
    -2.19
    咵
    -2.14
    퐼
    -2.11
    ctores
    -2.11
    螓
    -2.06
    微软
    -2.03
    datei
    -2.02
    POSITIVE LOGITS
    The
    2.83
     Virtually
    2.78
     Faced
    2.72
    and
    2.61
     Placing
    2.48
     Primarily
    2.47
     Widely
    2.45
     Practically
    2.44
     Roughly
    2.41
    2
    2.38
    Activations Density 0.001%

    No Known Activations