© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90169
    Prev
    Next
    INDEX
    Explanations

    converters, fencing, evidence

    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_34/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
    撈
    -0.75
    ンドン
    -0.73
     rozmiar
    -0.72
    ächt
    -0.71
     fibers
    -0.69
    idum
    -0.69
     réelle
    -0.69
    piles
    -0.68
     canals
    -0.67
     Möglich
    -0.66
    POSITIVE LOGITS
     SAR
    0.91
     ENO
    0.88
    Accurate
    0.81
     code
    0.79
    shuff
    0.78
    ರು
    0.77
    pcm
    0.76
    SAR
    0.75
     monoton
    0.75
     volante
    0.74
    Activations Density 0.029%

    No Known Activations