© 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. 31515
    Prev
    Next
    INDEX
    Explanations

    articles from medium about topological concepts

    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
     Senhor
    -0.79
     Instance
    -0.75
     PROCESSING
    -0.72
    pytest
    -0.71
     institutional
    -0.68
    eltzer
    -0.68
    🗿
    -0.67
    nucleus
    -0.66
    AMOS
    -0.66
     Processing
    -0.65
    POSITIVE LOGITS
    Dun
    0.74
     Dun
    0.73
     practice
    0.71
     Rob
    0.71
     cảm
    0.68
    YX
    0.68
     Far
    0.66
    Discrete
    0.65
     Blank
    0.65
     Sic
    0.65
    Activations Density 0.066%

    No Known Activations