© 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. 22-GEMMASCOPE-RES-131K
    7. 66008
    Prev
    Next
    INDEX
    Explanations

    such that OR of X

    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
     silueta
    -1.58
     dezelve
    -1.52
    iamo
    -1.50
     carcasa
    -1.48
     cintur
    -1.47
    とおり
    -1.46
     cordones
    -1.45
    者に
    -1.45
     coreano
    -1.44
     castillo
    -1.42
    POSITIVE LOGITS
     In
    1.30
     This
    1.20
    графии
    1.19
    鈑
    1.19
     również
    1.19
    Also
    1.18
    ний
    1.16
     также
    1.15
     recibirá
    1.14
     kommunizieren
    1.13
    Activations Density 0.057%

    No Known Activations