© 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. 118361
    Prev
    Next
    INDEX
    Explanations

    could not

    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
     vielmehr
    -1.00
    lograph
    -0.94
    eping
    -0.92
    nasi
    -0.90
    ומית
    -0.90
     可爱
    -0.85
    板块
    -0.85
    )²
    -0.83
    ataires
    -0.82
    )
    -0.81
    POSITIVE LOGITS
     not
    5.25
     не
    2.44
     नहीं
    1.98
     nicht
    1.91
    not
    1.91
     NOT
    1.89
     ikke
    1.84
     không
    1.80
     hardly
    1.70
    Not
    1.69
    Activations Density 0.030%

    No Known Activations