© 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. 10-GEMMASCOPE-RES-131K
    4. 41439
    Prev
    Next
    INDEX
    Explanations

    incorporation into

    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
     geschlagen
    -1.57
     wusste
    -1.45
    ci
    -1.45
     wußte
    -1.43
     ")
    
    -1.42
     ajustable
    -1.41
    The
    -1.41
    UPA
    -1.36
    疋
    -1.35
    io
    -1.33
    POSITIVE LOGITS
     into
    2.64
     in
    2.16
    跸
    1.77
     incorporates
    1.65
     incorporate
    1.60
    </b>
    1.52
     on
    1.51
    の魅力
    1.49
     include
    1.48
     econômica
    1.47
    Activations Density 0.139%

    No Known Activations