© 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. 69158
    Prev
    Next
    INDEX
    Explanations

    first + time unit

    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
    𓁹
    -1.87
     sooo
    -1.85
     soooo
    -1.84
    ⎆
    -1.84
    seems
    -1.81
    卨
    -1.79
    がなく
    -1.75
    ఽ
    -1.71
     REALLY
    -1.69
    
    -1.64
    POSITIVE LOGITS
     of
    2.33
     time
    2.22
     two
    1.89
     one
    1.80
     Each
    1.80
     Every
    1.78
     If
    1.76
     after
    1.75
     eight
    1.75
     days
    1.73
    Activations Density 0.037%

    No Known Activations