© 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. 82948
    Prev
    Next
    INDEX
    Explanations

    technical descriptive terms

    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
    corr
    -0.77
    mbert
    -0.71
     Altern
    -0.71
    界
    -0.68
    xref
    -0.66
    eltas
    -0.64
    wb
    -0.64
    шу
    -0.63
    onego
    -0.63
     Amore
    -0.61
    POSITIVE LOGITS
    âl
    0.78
     lej
    0.73
     dentelle
    0.73
     poupée
    0.73
    Responding
    0.73
     Purification
    0.72
    在她
    0.71
    待って
    0.71
     яйцо
    0.71
     Erwachsene
    0.71
    Activations Density 0.045%

    No Known Activations