© 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. 119058
    Prev
    Next
    INDEX
    Explanations

    caret position

    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
    collating
    -0.76
    部分
    -0.69
    散
    -0.67
    yaszt
    -0.66
     buon
    -0.66
     Tosh
    -0.66
    者
    -0.65
     sasa
    -0.64
    veille
    -0.64
    饼
    -0.64
    POSITIVE LOGITS
     Blocks
    0.79
    paragraph
    0.78
     blocks
    0.76
     Camino
    0.75
    ologe
    0.73
     paragraph
    0.73
     Тем
    0.70
     Incon
    0.70
     Mâ
    0.69
     yazar
    0.69
    Activations Density 0.074%

    No Known Activations