© 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. 112053
    Prev
    Next
    INDEX
    Explanations

    as followed by a role or descriptor

    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
     firft
    -1.46
    harapkan
    -1.34
    ids
    -1.33
    sió
    -1.32
    Algunos
    -1.30
     it
    -1.29
    ák
    -1.27
     something
    -1.27
     grecque
    -1.26
    ícia
    -1.25
    POSITIVE LOGITS
    帙
    1.30
    開始
    1.29
     zwar
    1.28
    而
    1.28
     “
    1.28
     —
    1.27
     และ
    1.27
    acheter
    1.25
    фіка
    1.25
    ciating
    1.23
    Activations Density 0.019%

    No Known Activations