© 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. 76302
    Prev
    Next
    INDEX
    Explanations

    set background color

    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
    outi
    -0.88
    adine
    -0.86
    chill
    -0.79
    invalidate
    -0.77
    acters
    -0.77
     setState
    -0.76
     consciente
    -0.75
     vitales
    -0.75
    τη
    -0.75
    ared
    -0.75
    POSITIVE LOGITS
     hidden
    1.32
     user
    1.16
    backgroundColor
    1.15
    hidden
    1.13
     Hidden
    0.97
     highlighted
    0.94
    user
    0.91
    Hidden
    0.91
     concealed
    0.89
     when
    0.86
    Activations Density 0.007%

    No Known Activations