© 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. 99931
    Prev
    Next
    INDEX
    Explanations

    numbers indicating order or degree

    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
     getView
    -0.89
    urre
    -0.69
     المث
    -0.69
     tzw
    -0.69
     силу
    -0.68
     Ten
    -0.68
    slim
    -0.68
     granos
    -0.67
    τός
    -0.66
    uby
    -0.66
    POSITIVE LOGITS
     second
    2.78
     fourth
    2.58
     third
    2.56
     order
    2.50
    Second
    2.33
     Second
    2.31
    second
    2.27
     sixth
    2.06
     fifth
    2.06
     Third
    2.05
    Activations Density 0.081%

    No Known Activations