© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40405
    Prev
    Next
    INDEX
    Explanations

    road safety and traffic

    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_10/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
     ‘‘
    -2.09
    ℟
    -1.87
    bernador
    -1.81
    </h2>
    -1.80
    䊊
    -1.77
    就像是
    -1.73
    PLAUSE
    -1.66
    ⽥
    -1.63
          
    -1.63
    缐
    -1.57
    POSITIVE LOGITS
    '
    2.19
     mishap
    2.03
     '
    2.00
    ch
    1.97
    ...."
    1.91
    你
    1.85
    us
    1.84
    road
    1.82
    .."
    1.81
    _'
    1.81
    Activations Density 0.029%

    No Known Activations