© 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. 79765
    Prev
    Next
    INDEX
    Explanations

    technical terms often followed by punctuation or keywords

    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
     comuni
    -1.05
     maniere
    -1.05
    humidité
    -1.02
     häufiger
    -0.99
     alimentare
    -0.97
    為に
    -0.95
    entraî
    -0.94
     castig
    -0.93
     Tài
    -0.92
    identité
    -0.92
    POSITIVE LOGITS
     as
    0.96
     möjligt
    0.91
     from
    0.90
     an
    0.89
     mostly
    0.87
     mainly
    0.86
    ician
    0.84
     partly
    0.81
     dlaczego
    0.80
     chiefly
    0.79
    Activations Density 0.071%

    No Known Activations