© 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. 76359
    Prev
    Next
    INDEX
    Explanations

    market places 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
    ’;
    -0.98
     Anſ
    -0.96
    Rein
    -0.88
    ’
    -0.87
    あん
    -0.85
     жид
    -0.84
    要把
    -0.84
    ’.
    -0.84
    ALERT
    -0.83
     pran
    -0.82
    POSITIVE LOGITS
     place
    2.03
    place
    1.79
     segment
    1.38
    places
    1.30
    PLACE
    1.28
    plaats
    1.27
    Place
    1.26
     segmentation
    1.26
     niche
    1.25
     share
    1.21
    Activations Density 0.023%

    No Known Activations