© 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. 34-GEMMASCOPE-RES-131K
    4. 55956
    Prev
    Next
    INDEX
    Explanations

    code structure identifiers

    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
     lecteur
    -0.74
     ferrous
    -0.71
    isamment
    -0.71
     серпня
    -0.68
    Clause
    -0.67
     udě
    -0.67
     Closet
    -0.67
    gana
    -0.66
     Patri
    -0.66
     FSC
    -0.66
    POSITIVE LOGITS
     хру
    0.75
    viers
    0.68
    出力
    0.65
     mapping
    0.65
     productive
    0.64
    дим
    0.63
     hạ
    0.63
    珍珠
    0.63
    andalf
    0.62
     rest
    0.62
    Activations Density 0.066%

    No Known Activations