© 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. 10-GEMMASCOPE-RES-131K
    7. 101205
    Prev
    Next
    INDEX
    Explanations

    origin of

    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_10/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
    猻
    -1.64
     gracios
    -1.60
    鴴
    -1.55
     amorosa
    -1.50
    他的
    -1.48
    說
    -1.45
     Wirksamkeit
    -1.43
     versátil
    -1.42
    幛
    -1.42
    ܆
    -1.41
    POSITIVE LOGITS
     of
    3.44
     from
    2.03
     for
    1.70
    之意
    1.49
     are
    1.48
     sebaik
    1.41
     kemarin
    1.36
    瞼
    1.35
     at
    1.34
    而又
    1.34
    Activations Density 0.024%

    No Known Activations