© 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. 7369
    Prev
    Next
    INDEX
    Explanations

    Wester, Vander, Sey names

    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
     coupled
    -2.55
    ágen
    -2.53
    )’
    -2.47
     of
    -2.44
    '
    -2.41
    鴈
    -2.41
     alrededores
    -2.34
     protegido
    -2.33
    橈
    -2.31
     solicitado
    -2.30
    POSITIVE LOGITS
    ll
    3.30
    为了
    2.97
    o
    2.86
     —
    2.83
    if
    2.78
    s
    2.78
     prioriti
    2.75
    聳
    2.72
    9
    2.72
        
    2.70
    Activations Density 0.008%

    No Known Activations