© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39104
    Prev
    Next
    INDEX
    Explanations

    control systems and algorithms

    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
     blanches
    -1.63
    几个人
    -1.47
    有趣的
    -1.45
     citoyens
    -1.45
     díky
    -1.44
     ménages
    -1.44
    闩
    -1.44
     Eigentü
    -1.43
    最后由
    -1.41
    laquo
    -1.41
    POSITIVE LOGITS
    ;
    1.64
    5
    1.46
     at
    1.41
    也
    1.38
     to
    1.38
    IonicModule
    1.36
     also
    1.35
    都
    1.30
    -]
    1.29
     Diarsipkan
    1.27
    Activations Density 0.041%

    No Known Activations