© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106905
    Prev
    Next
    INDEX
    Explanations

    URLs and email addresses

    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
    oxford
    -0.91
    pav
    -0.86
    _"
    -0.86
    cartier
    -0.85
    bunal
    -0.84
     腕
    -0.83
    يكب
    -0.83
    рюкзак
    -0.82
    cortina
    -0.81
     obowią
    -0.81
    POSITIVE LOGITS
     sites
    1.18
     websites
    1.17
    www
    1.07
     http
    1.05
    sites
    1.01
     website
    1.00
    http
    0.93
     blogs
    0.93
    web
    0.93
     web
    0.91
    Activations Density 0.016%

    No Known Activations