© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70395
    Prev
    Next
    INDEX
    Explanations

    depth or deepness

    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
     There
    -1.98
     類
    -1.55
     preciosas
    -1.51
     Slowly
    -1.50
     невели
    -1.49
     Already
    -1.48
     Almost
    -1.48
     Another
    -1.47
     Surprisingly
    -1.47
     Probably
    -1.45
    POSITIVE LOGITS
     \
    2.02
     and
    1.83
    \
    1.64
     depth
    1.52
    はこの
    1.51
     of
    1.47
    </b>
    1.42
    end
    1.41
    来找
    1.39
    你不要
    1.38
    Activations Density 0.017%

    No Known Activations