© 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. 4317
    Prev
    Next
    INDEX
    Explanations

    license text

    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
    refle
    -0.78
     *
    -0.75
     Pendant
    -0.69
     енер
    -0.68
    *
    -0.68
     jeunesse
    -0.67
    ᥆
    -0.66
     blinded
    -0.65
    muss
    -0.65
    AGGIO
    -0.65
    POSITIVE LOGITS
    [][]
    0.81
    valently
    0.75
     [][]
    0.69
    拓展
    0.68
     (~
    0.68
    ston
    0.67
    ounds
    0.66
    oglo
    0.63
    vā
    0.63
    optimized
    0.63
    Activations Density 0.059%

    No Known Activations