© 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. 34-GEMMASCOPE-RES-131K
    7. 108559
    Prev
    Next
    INDEX
    Explanations

    tug and related words

    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
     burst
    -0.75
    ⼊
    -0.75
    vances
    -0.75
     خصوصی
    -0.74
     fungus
    -0.73
     mushroom
    -0.71
    كس
    -0.70
     mutta
    -0.69
    ixer
    -0.69
    robust
    -0.68
    POSITIVE LOGITS
     tug
    1.66
     Tug
    1.34
    Tug
    1.23
    tug
    1.19
    boat
    0.80
     ropes
    0.76
     Gegen
    0.74
    boats
    0.74
     Matching
    0.74
    Matching
    0.73
    Activations Density 0.026%

    No Known Activations