© 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. 76974
    Prev
    Next
    INDEX
    Explanations

    pulling

    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
     Zweifel
    -0.72
    流し
    -0.67
     Ritter
    -0.67
     básicas
    -0.66
    eb
    -0.66
    ناه
    -0.65
    ござい
    -0.64
    olysis
    -0.63
    енный
    -0.63
    عرِّف
    -0.63
    POSITIVE LOGITS
     pull
    3.23
     pulled
    3.14
    pull
    3.13
    Pull
    2.91
     Pull
    2.88
     pulls
    2.88
     pulling
    2.80
    pulled
    2.53
    取出
    2.45
     Pulling
    2.39
    Activations Density 0.061%

    No Known Activations