© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45582
    Prev
    Next
    INDEX
    Explanations

    kon and kong variants

    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
     my
    -0.71
    una
    -0.69
     brag
    -0.69
     rhyme
    -0.69
    Collector
    -0.67
     breath
    -0.67
    assertFalse
    -0.66
    téri
    -0.66
    firebase
    -0.65
    foam
    -0.65
    POSITIVE LOGITS
     kon
    0.93
     Kon
    0.89
    Kon
    0.85
    Кон
    0.84
     KON
    0.81
     контра
    0.80
    igs
    0.76
     Кон
    0.75
     helpline
    0.75
    kow
    0.74
    Activations Density 0.014%

    No Known Activations