© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36707
    Prev
    Next
    INDEX
    Explanations

    public statements and events

    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
     dlaczego
    -0.96
     trám
    -0.94
     actuales
    -0.93
     verlä
    -0.92
    hmen
    -0.92
     protože
    -0.91
    ᯾
    -0.91
    pertino
    -0.91
     rám
    -0.90
    cipline
    -0.90
    POSITIVE LOGITS
     public
    1.63
     pública
    1.42
     visible
    1.40
    public
    1.35
     PUBLIC
    1.30
     publicly
    1.28
    公開
    1.16
     veřej
    1.16
    Public
    1.09
    visible
    1.09
    Activations Density 0.065%

    No Known Activations