© 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. 106666
    Prev
    Next
    INDEX
    Explanations

    places and their distribution

    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
     Anywhere
    -1.54
     Everywhere
    -1.45
    anywhere
    -1.42
    everywhere
    -1.40
    Anywhere
    -1.29
    Everywhere
    -1.28
     everywhere
    -1.23
     anywhere
    -1.19
     Elsewhere
    -1.03
     überall
    -0.97
    POSITIVE LOGITS
     around
    3.55
     alrededor
    1.90
    around
    1.83
    Around
    1.82
     across
    1.79
     Around
    1.75
     autour
    1.66
     حول
    1.57
     rundt
    1.47
     intorno
    1.46
    Activations Density 0.067%

    No Known Activations