© 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. 39391
    Prev
    Next
    INDEX
    Explanations

    unavailable, missing, or affected

    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
     particolare
    -0.87
    tences
    -0.87
     denselben
    -0.84
     geralmente
    -0.81
    idencia
    -0.81
     baseado
    -0.80
    žad
    -0.80
    消灭
    -0.79
    าก
    -0.79
    maxWidth
    -0.78
    POSITIVE LOGITS
     unavailable
    1.41
     vital
    1.20
     missing
    1.09
     essential
    0.99
    MISSING
    0.94
     due
    0.94
     temporarily
    0.92
     affected
    0.91
    Unavailable
    0.87
    詫
    0.87
    Activations Density 0.108%

    No Known Activations