© 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. 130089
    Prev
    Next
    INDEX
    Explanations

    soon after

    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
    幛
    -1.76
    尨
    -1.73
     atractiva
    -1.67
    FORME
    -1.66
    
    -1.65
    땃
    -1.61
    뗄
    -1.60
    鸲
    -1.57
    ⸱
    -1.56
    erializer
    -1.55
    POSITIVE LOGITS
     before
    2.22
     after
    2.17
    f
    2.06
     when
    1.88
     on
    1.86
    l
    1.80
     That
    1.79
     the
    1.76
    t
    1.76
    e
    1.74
    Activations Density 0.036%

    No Known Activations