© 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. 93551
    Prev
    Next
    INDEX
    Explanations

    association and outcomes

    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
     Epile
    -1.27
    転車
    -1.06
     epile
    -1.06
    +'.
    -1.06
    carus
    -1.03
    膵
    -0.97
     Epilepsy
    -0.95
    moiselle
    -0.94
    +".
    -0.94
     soin
    -0.94
    POSITIVE LOGITS
     outcomes
    1.45
     outcome
    1.37
     risk
    1.15
     childhood
    1.14
     early
    1.13
     increased
    1.11
     gender
    1.11
     patients
    1.06
     treatment
    1.06
     long
    1.05
    Activations Density 0.916%

    No Known Activations