© 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. 22-GEMMASCOPE-RES-131K
    7. 66702
    Prev
    Next
    INDEX
    Explanations

    ionic plugins and pages

    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_22/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
    '
    -1.30
    a
    -1.09
     universite
    -1.08
     mentales
    -1.08
     makam
    -1.05
    <h2>
    -1.03
    ​​
    -1.00
     ル
    -0.98
     klima
    -0.98
    </h2>
    -0.97
    POSITIVE LOGITS
     गरे
    1.32
    曲は
    1.20
    Ferien
    1.20
     тема
    1.19
     vzor
    1.18
    Untuk
    1.18
    Prijs
    1.18
    鏤
    1.18
    ांकि
    1.18
    avimas
    1.16
    Activations Density 0.006%

    No Known Activations