© 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. 53959
    Prev
    Next
    INDEX
    Explanations

    license and code structure

    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
    TYPE
    -0.88
    Lot
    -0.73
    refer
    -0.72
     typu
    -0.68
    筅
    -0.68
     TYPE
    -0.66
    potranspiration
    -0.66
    cendo
    -0.66
    resten
    -0.66
    lapp
    -0.65
    POSITIVE LOGITS
     Monique
    0.68
    Monique
    0.67
    nestjs
    0.66
     Extension
    0.66
    VIE
    0.65
    ez
    0.64
    waran
    0.64
     privileged
    0.63
     Rugged
    0.63
     loading
    0.63
    Activations Density 0.086%

    No Known Activations