© 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. 34-GEMMASCOPE-RES-131K
    7. 6868
    Prev
    Next
    INDEX
    Explanations

    times, multiples, and scaling

    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_34/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
    $\%
    -0.76
     zweier
    -0.76
    millions
    -0.75
    rsch
    -0.73
     Thousands
    -0.73
    нительно
    -0.71
     Kna
    -0.69
     ajudam
    -0.69
    离婚
    -0.69
     SOCK
    -0.68
    POSITIVE LOGITS
     multiplier
    2.20
    倍
    2.03
     multipliers
    1.84
    multiplier
    1.70
     times
    1.70
     multiples
    1.64
     Multiplier
    1.59
     倍
    1.45
    Times
    1.45
     Times
    1.41
    Activations Density 0.028%

    No Known Activations