© 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. 99139
    Prev
    Next
    INDEX
    Explanations

    Marianne Faithfull layouts subplots paginate

    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
    镚
    -2.28
     Wszyst
    -2.13
    掠
    -2.11
     básicamente
    -2.03
     tendremos
    -2.00
    ânsito
    -1.98
    пи
    -1.95
    </sup>
    -1.94
     
    -1.94
    ે
    -1.93
    POSITIVE LOGITS
    ’
    2.83
    ⬯
    2.52
    沨
    2.42
    d
    2.28
    之际
    2.27
     offizielle
    2.23
    as
    2.19
     vorhand
    2.19
     lequel
    2.17
     zobac
    2.16
    Activations Density 0.002%

    No Known Activations