© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70813
    Prev
    Next
    INDEX
    Explanations

    special codes or locations

    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
    が
    -0.98
     agrí
    -0.97
     territo
    -0.96
     was
    -0.96
     Wurzeln
    -0.94
    вої
    -0.94
     enem
    -0.93
     Italiana
    -0.92
     científicas
    -0.91
    に
    -0.91
    POSITIVE LOGITS
    وث
    0.99
     fakty
    0.93
     and
    0.92
     cortada
    0.91
     cubrir
    0.91
     sentirse
    0.90
     mentiras
    0.89
     mismas
    0.89
     ocurrir
    0.88
     используются
    0.88
    Activations Density 0.108%

    No Known Activations