© 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. 34586
    Prev
    Next
    INDEX
    Explanations

    compact car segments

    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
    rische
    -0.83
     riqueza
    -0.80
    čke
    -0.79
     TreeSet
    -0.76
     céré
    -0.75
    tispiece
    -0.75
    äld
    -0.73
     seizoen
    -0.73
    オリジナル
    -0.72
    loggedin
    -0.71
    POSITIVE LOGITS
     segment
    1.91
     compact
    1.80
     Compact
    1.74
    compact
    1.62
    segment
    1.52
    Compact
    1.52
     Segment
    1.48
     segments
    1.47
    Segment
    1.47
     kompak
    1.34
    Activations Density 0.023%

    No Known Activations