© 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. 118438
    Prev
    Next
    INDEX
    Explanations

    book publishing details

    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
     aquarium
    -0.76
    poll
    -0.76
    Rit
    -0.75
    ,~
    -0.74
     katholischen
    -0.72
    끫
    -0.72
     bronco
    -0.72
    strncmp
    -0.71
     canel
    -0.71
     clandestine
    -0.69
    POSITIVE LOGITS
     starred
    0.80
     kita
    0.78
     dominio
    0.77
     peduli
    0.75
     Thema
    0.74
     tranh
    0.73
     merken
    0.72
     solides
    0.71
    花的
    0.71
     marca
    0.70
    Activations Density 0.023%

    No Known Activations