© 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. 101061
    Prev
    Next
    INDEX
    Explanations

    maintaining a state or continuing

    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
     serão
    -1.47
    会在
    -1.35
     bestimmten
    -1.35
     contará
    -1.34
    (“
    -1.31
     ajudam
    -1.30
    にしても
    -1.27
    ꯥ
    -1.27
     algún
    -1.25
     egreg
    -1.23
    POSITIVE LOGITS
     toks
    1.21
    re
    1.21
     isn
    1.18
     aren
    1.16
     orel
    1.16
     he
    1.15
     doesn
    1.13
     Not
    1.13
    >
    1.12
     as
    1.10
    Activations Density 0.038%

    No Known Activations