© 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. 93681
    Prev
    Next
    INDEX
    Explanations

    institutions or locations

    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
    鶿
    -2.41
    
    -2.41
     pérd
    -2.39
     própri
    -2.39
    ఝ
    -2.36
    镲
    -2.27
    
    -2.20
    ￬
    -2.20
     utiliser
    -2.19
     acheter
    -2.19
    POSITIVE LOGITS
     in
    3.42
     with
    3.30
     at
    3.25
     on
    3.14
     from
    3.06
     or
    2.98
     for
    2.97
     which
    2.97
     during
    2.92
     without
    2.92
    Activations Density 0.104%

    No Known Activations