© 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. 54096
    Prev
    Next
    INDEX
    Explanations

    warranty or liability

    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
     mobiliario
    -0.70
    toad
    -0.69
     descubrió
    -0.68
    Aries
    -0.68
    maran
    -0.66
    Autores
    -0.66
     "("
    -0.66
    hasOwnProperty
    -0.66
     efficacious
    -0.66
    verride
    -0.65
    POSITIVE LOGITS
     hilo
    0.76
     Fal
    0.74
     Legacy
    0.72
    nych
    0.71
     Projects
    0.70
    iod
    0.70
     pro
    0.70
    threads
    0.69
     wym
    0.69
    ੂ
    0.69
    Activations Density 0.044%

    No Known Activations