© 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. 34-GEMMASCOPE-RES-131K
    7. 64957
    Prev
    Next
    INDEX
    Explanations

    decrease or reverse direction

    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
     upstairs
    -0.87
    の上
    -0.86
    numerator
    -0.85
    lceil
    -0.83
     gór
    -0.82
    (++
    -0.82
    sser
    -0.80
    [++
    -0.79
     表情
    -0.77
    钢琴
    -0.77
    POSITIVE LOGITS
     negative
    1.43
     négatif
    1.14
     reverse
    1.11
     inverse
    1.10
     inversa
    1.09
    negative
    1.07
    Conversely
    1.05
     negativo
    1.05
     inversely
    1.05
     negatif
    1.04
    Activations Density 0.059%

    No Known Activations