© 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. 22-GEMMASCOPE-RES-131K
    7. 39047
    Prev
    Next
    INDEX
    Explanations

    realistic and true descriptions

    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
    ⚽
    -1.02
     systemctl
    -0.95
    form
    -0.95
    ANC
    -0.93
    repo
    -0.93
    ────
    -0.91
     marts
    -0.90
    MLS
    -0.89
     FUNERAL
    -0.89
    ources
    -0.89
    POSITIVE LOGITS
     realistic
    1.61
    realistic
    1.43
     Realistic
    1.39
     реаль
    1.36
    真实
    1.32
    真实的
    1.32
     typical
    1.30
    reality
    1.28
    Realistic
    1.27
    真實
    1.22
    Activations Density 0.096%

    No Known Activations