© 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. 9045
    Prev
    Next
    INDEX
    Explanations

    pods and pod spec

    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
    which
    -3.22
    賒
    -3.03
    鸶
    -3.00
    椟
    -3.00
    脔
    -2.72
     Houſe
    -2.50
    gées
    -2.45
    that
    -2.45
    Ⲉ
    -2.44
    you
    -2.42
    POSITIVE LOGITS
    \
    4.00
    {
    3.52
    /
    2.73
     If
    2.38
     με
    2.36
    }$
    2.31
     extranjera
    2.27
    —
    2.27
    ’
    2.27
     has
    2.14
    Activations Density 0.008%

    No Known Activations