© 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. 25515
    Prev
    Next
    INDEX
    Explanations

    published

    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
     very
    -1.28
     sophisticated
    -1.18
     mysterious
    -1.18
     bied
    -1.11
     famous
    -1.09
    isticated
    -1.06
    CRIPTION
    -1.05
     modeli
    -1.01
     querida
    -1.00
     longstanding
    -1.00
    POSITIVE LOGITS
     occafion
    1.32
    ējās
    1.29
    regardless
    1.27
    ært
    1.15
     Betrachtung
    1.10
    那些
    1.09
    간
    1.09
    дцать
    1.08
    having
    1.06
    jir
    1.06
    Activations Density 0.694%

    No Known Activations