© 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. 90941
    Prev
    Next
    INDEX
    Explanations

    agreement and contract terms

    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
    ^*$
    -0.83
    ariz
    -0.77
    bague
    -0.77
    窮
    -0.75
     detergent
    -0.75
    casco
    -0.75
    appar
    -0.75
    езда
    -0.74
     outcomes
    -0.74
    yung
    -0.74
    POSITIVE LOGITS
     orally
    0.92
    previous
    0.88
    terea
    0.86
    aneous
    0.84
    ùy
    0.80
    rentino
    0.80
     Waiver
    0.79
     verbal
    0.79
     waiver
    0.78
    ớp
    0.78
    Activations Density 0.012%

    No Known Activations