© 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. 80756
    Prev
    Next
    INDEX
    Explanations

    Mark Sutherland, Two-week, Design And

    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
     Bd
    -0.82
    Fred
    -0.74
     Ergebnis
    -0.72
    rops
    -0.71
    Role
    -0.71
     शुरु
    -0.70
    Жи
    -0.69
    helo
    -0.68
    Mo
    -0.67
    descriptor
    -0.67
    POSITIVE LOGITS
     relay
    1.01
    Relay
    0.97
     Relay
    0.96
    relay
    0.93
    tv
    0.87
    tir
    0.84
     kart
    0.81
    mutant
    0.81
    kart
    0.81
     infrar
    0.79
    Activations Density 0.013%

    No Known Activations