© 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. 84427
    Prev
    Next
    INDEX
    Explanations

    numbers and completion

    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
     Serie
    -0.76
     attacker
    -0.73
    Tare
    -0.68
     Deportes
    -0.65
    ours
    -0.65
    ėtų
    -0.65
    Lij
    -0.65
     Dire
    -0.65
     Services
    -0.64
    同期
    -0.64
    POSITIVE LOGITS
     âu
    0.75
     maneuvering
    0.74
    ocene
    0.68
     jednost
    0.67
     ejecutivo
    0.66
     llevará
    0.65
    ahara
    0.65
    élément
    0.64
    ++$
    0.64
    component
    0.64
    Activations Density 0.070%

    No Known Activations