© 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. 10267
    Prev
    Next
    INDEX
    Explanations

    specific examples following "especially" or "particularly"

    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
     it
    -2.22
     or
    -1.92
     same
    -1.77
     if
    -1.70
     there
    -1.58
     natomiast
    -1.52
     and
    -1.52
     baloncesto
    -1.50
     albeit
    -1.47
     see
    -1.44
    POSITIVE LOGITS
     our
    1.88
    衚
    1.70
     Songtext
    1.64
    which
    1.61
    from
    1.57
     может
    1.55
     modele
    1.55
    윽
    1.54
     Peut
    1.53
    bandicam
    1.52
    Activations Density 0.045%

    No Known Activations