© 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. 103197
    Prev
    Next
    INDEX
    Explanations

    setState followed by string

    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
    Medida
    -0.81
     служ
    -0.81
     folgt
    -0.80
    财经
    -0.80
    Schon
    -0.79
    Pens
    -0.79
    直至
    -0.79
     кислота
    -0.77
    Mandy
    -0.77
     ortaya
    -0.77
    POSITIVE LOGITS
    ({
    1.54
    setState
    1.02
     state
    0.96
    ₂,
    0.94
     ({
    0.93
     states
    0.89
    ({
    0.88
    立派
    0.88
     budynku
    0.85
    KO
    0.85
    Activations Density 0.001%

    No Known Activations