© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64134
    Prev
    Next
    INDEX
    Explanations

    wireless networking standards

    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
     classified
    -0.85
    害怕
    -0.78
     Jehovah
    -0.74
    inak
    -0.73
    empt
    -0.72
     prosecutor
    -0.69
     Folgen
    -0.69
    สนใจ
    -0.69
     HM
    -0.68
     ct
    -0.67
    POSITIVE LOGITS
     WPS
    0.90
    Genes
    0.84
    CardNumber
    0.82
     Recycled
    0.82
    shorts
    0.79
     tess
    0.78
    "},
    0.77
    Infrastructure
    0.74
    caz
    0.74
     biotite
    0.73
    Activations Density 0.029%

    No Known Activations