© 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. 59005
    Prev
    Next
    INDEX
    Explanations

    measure or evaluate current state

    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
    ếp
    -0.83
    IDA
    -0.77
     Haddad
    -0.74
    ohio
    -0.74
    lighet
    -0.73
    lados
    -0.73
    ῦ
    -0.73
    urers
    -0.72
     écran
    -0.71
    úi
    -0.71
    POSITIVE LOGITS
     pulse
    3.09
     barometer
    2.95
    pulse
    2.63
     temperature
    2.52
     gauge
    2.42
    Pulse
    2.33
     Pulse
    2.30
    temperature
    2.03
     thermometer
    1.98
     Temperature
    1.91
    Activations Density 0.058%

    No Known Activations