© 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. 66364
    Prev
    Next
    INDEX
    Explanations

    code structure definitions and types

    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
    pub
    -1.25
    Pub
    -1.00
     pub
    -0.98
     Pub
    -0.94
     puberty
    -0.92
     publico
    -0.90
     Affects
    -0.86
     dispositifs
    -0.84
    श्य
    -0.81
     PUB
    -0.80
    POSITIVE LOGITS
     type
    1.16
    type
    0.97
     her
    0.85
     leverage
    0.78
     types
    0.77
     (#
    0.75
     Type
    0.75
     heridas
    0.75
    prilis
    0.74
     neck
    0.73
    Activations Density 0.005%

    No Known Activations