© 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. 124619
    Prev
    Next
    INDEX
    Explanations

    reporting demonstrated results

    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
     chré
    -1.80
    閦
    -1.74
    🧌
    -1.73
    却又
    -1.65
    cznych
    -1.61
     cualidades
    -1.60
     bepaalde
    -1.59
     """
    -1.58
     limitaciones
    -1.57
    鋮
    -1.55
    POSITIVE LOGITS
     one
    1.77
     its
    1.53
     a
    1.41
     without
    1.39
     that
    1.38
     eleições
    1.35
    :
    1.33
     ३
    1.32
     regardless
    1.30
     including
    1.30
    Activations Density 0.215%

    No Known Activations