© 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. 22-GEMMASCOPE-RES-131K
    7. 130259
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_22/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
     dát
    -1.06
     déchir
    -1.02
    Mua
    -1.02
     pán
    -0.99
     télécharge
    -0.96
    cadre
    -0.95
    嚅
    -0.94
     pétrole
    -0.94
     vodu
    -0.94
     gminy
    -0.93
    POSITIVE LOGITS
     in
    1.27
     we
    0.94
     as
    0.88
     then
    0.87
     happy
    0.86
     examined
    0.86
     if
    0.85
     on
    0.83
     Or
    0.82
     immediately
    0.82
    Activations Density 0.188%

    No Known Activations