© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116336
    Prev
    Next
    INDEX
    Explanations

    TypeInfo. followed by identifier

    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
    ныя
    -0.70
    瓜
    -0.69
     pelajar
    -0.68
     deterrent
    -0.65
    tagez
    -0.65
    nextPage
    -0.63
    FEC
    -0.63
     máquinas
    -0.62
     sementes
    -0.61
     saudara
    -0.61
    POSITIVE LOGITS
     honey
    0.71
    iens
    0.69
     mane
    0.68
     Honey
    0.68
     σχε
    0.67
     schedule
    0.66
     kud
    0.66
     stuck
    0.66
     ce
    0.66
     Lighthouse
    0.66
    Activations Density 0.068%

    No Known Activations