© 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. 91221
    Prev
    Next
    INDEX
    Explanations

    code file headers and data structures

    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
    Ingestion
    -0.70
     entry
    -0.67
     occupancy
    -0.65
    ȴ
    -0.65
     occupy
    -0.65
    psico
    -0.64
     suction
    -0.63
     occupied
    -0.62
    versal
    -0.61
     ocupar
    -0.60
    POSITIVE LOGITS
    rások
    0.78
    pow
    0.72
    раи
    0.69
     thủ
    0.69
     Álvaro
    0.68
    otus
    0.68
    drawImage
    0.68
     沖縄
    0.68
    elyk
    0.68
     Frontera
    0.67
    Activations Density 0.047%

    No Known Activations