© 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. 70252
    Prev
    Next
    INDEX
    Explanations

    tow or towing

    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
    which
    -3.38
    Is
    -3.34
    .
    -3.20
    ized
    -3.06
    Of
    -3.00
    In
    -2.94
    Which
    -2.88
    er
    -2.84
    咴
    -2.59
    Has
    -2.55
    POSITIVE LOGITS
    薷
    3.47
    刂
    2.80
    逦
    2.77
     decenas
    2.64
    釤
    2.58
    medriver
    2.55
    
    2.55
    eſt
    2.55
    骉
    2.53
    AddTagHelper
    2.52
    Activations Density 0.003%

    No Known Activations