© 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. 118029
    Prev
    Next
    INDEX
    Explanations

    image or likeness

    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
    ctivos
    -0.75
    MEDIATE
    -0.70
    BIBLIOGRAPHY
    -0.68
    脐
    -0.68
     BEHAVIOR
    -0.66
     temporales
    -0.66
     POINTS
    -0.65
     Macquarie
    -0.65
    LAY
    -0.64
     fractionation
    -0.64
    POSITIVE LOGITS
     likeness
    4.75
     image
    4.06
    image
    3.25
     liken
    3.13
     Image
    2.73
    liken
    2.72
    Image
    2.61
     imagem
    2.45
     Lik
    2.42
     images
    2.30
    Activations Density 0.030%

    No Known Activations