© 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. 49444
    Prev
    Next
    INDEX
    Explanations

    and connectors

    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
    řeba
    -0.81
    Jel
    -0.80
    ͪ
    -0.80
    や
    -0.80
    Hubert
    -0.75
    comparator
    -0.74
    Aro
    -0.73
    Fim
    -0.72
    ás
    -0.72
    emailAddress
    -0.70
    POSITIVE LOGITS
    )&&
    1.86
    并
    1.80
    And
    1.67
     And
    1.57
     และ
    1.55
    并且
    1.55
     &&
    1.52
     并
    1.44
    そして
    1.37
    並且
    1.34
    Activations Density 0.149%

    No Known Activations