© 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. 55692
    Prev
    Next
    INDEX
    Explanations

    off the field

    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
    RuntimeException
    -0.71
    mbio
    -0.69
    ünsche
    -0.68
    │
    -0.67
    yeth
    -0.67
    stus
    -0.66
     प्रोड
    -0.65
    tské
    -0.65
     neque
    -0.64
    illiers
    -0.63
    POSITIVE LOGITS
     off
    7.69
    Off
    5.53
     Off
    5.25
    off
    5.00
     OFF
    4.59
    OFF
    3.98
    オフ
    3.50
    offs
    2.84
     offs
    2.81
     ऑफ
    2.81
    Activations Density 0.101%

    No Known Activations