© 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. 22-GEMMASCOPE-RES-131K
    7. 33213
    Prev
    Next
    INDEX
    Explanations

    Blanton

    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
     rác
    -1.06
     Decrease
    -1.04
     reacties
    -1.01
     apprécier
    -1.01
    prender
    -0.98
     berücksich
    -0.97
     Federación
    -0.96
     khoe
    -0.96
    っちゃった
    -0.96
     continú
    -0.96
    POSITIVE LOGITS
    alties
    0.92
    ients
    0.91
     GOOD
    0.90
     that
    0.89
     as
    0.88
    ̀
    0.88
    ;
    0.88
    rechten
    0.87
    foods
    0.86
     time
    0.85
    Activations Density 0.016%

    No Known Activations