© 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. 83764
    Prev
    Next
    INDEX
    Explanations

    Michael, Sensor, Gas, Q, Quality

    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
     snail
    -0.81
     thùng
    -0.80
     Exposure
    -0.80
    🧺
    -0.79
    宝宝
    -0.79
    musik
    -0.79
    Vy
    -0.76
     SON
    -0.76
    znego
    -0.76
     Зна
    -0.76
    POSITIVE LOGITS
    enso
    0.73
     beginning
    0.73
     continuous
    0.71
     dirigente
    0.69
     Fahrrad
    0.69
     seen
    0.69
    BuildContext
    0.69
     censi
    0.69
    ListTile
    0.69
     remains
    0.68
    Activations Density 0.005%

    No Known Activations