© 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. 34-GEMMASCOPE-RES-131K
    7. 64635
    Prev
    Next
    INDEX
    Explanations

    market and related fields

    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
    edipus
    -0.79
     ih
    -0.78
    crab
    -0.74
    blooming
    -0.74
    enst
    -0.72
     поки
    -0.71
     Romana
    -0.70
     жа
    -0.69
    看看
    -0.69
     billede
    -0.68
    POSITIVE LOGITS
    ůvod
    0.89
    conjugated
    0.80
     deth
    0.79
     threes
    0.77
     appartient
    0.77
    釐
    0.77
    떄
    0.77
     ethically
    0.75
     brisk
    0.75
     facilitators
    0.75
    Activations Density 0.015%

    No Known Activations