© 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. 50277
    Prev
    Next
    INDEX
    Explanations

    css colors

    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
     left
    -1.40
     Left
    -1.27
    Left
    -1.26
    LEFT
    -1.23
    Top
    -1.21
     top
    -1.17
     Top
    -1.14
    left
    -1.09
    top
    -1.01
     TOP
    -0.98
    POSITIVE LOGITS
     premières
    0.84
    Smoke
    0.84
     sauter
    0.82
     smoke
    0.82
    golden
    0.81
     雪
    0.79
     bohat
    0.77
    atro
    0.77
     golden
    0.77
     gitara
    0.77
    Activations Density 0.019%

    No Known Activations