© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38501
    Prev
    Next
    INDEX
    Explanations

    pushing

    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
    傳統
    -0.88
    機會
    -0.88
    spiel
    -0.81
    ただ
    -0.79
    reff
    -0.77
    perhaps
    -0.75
    itures
    -0.74
    obut
    -0.74
    nation
    -0.72
    нів
    -0.71
    POSITIVE LOGITS
     pushing
    0.98
     shove
    0.98
     Pus
    0.92
     shoving
    0.90
     Push
    0.89
    Pus
    0.87
     pushes
    0.85
     betterment
    0.84
    Push
    0.83
    Pushing
    0.83
    Activations Density 0.014%

    No Known Activations