© 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. 31347
    Prev
    Next
    INDEX
    Explanations

    byte slices

    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
     and
    -1.18
     岁
    -0.91
     [
    -0.86
     see
    -0.84
    velocityY
    -0.83
     AND
    -0.82
     have
    -0.81
     Now
    -0.80
     счета
    -0.80
     ind
    -0.78
    POSITIVE LOGITS
    byte
    1.25
     vaisseaux
    1.14
     êtres
    1.07
     génér
    1.04
     modèles
    1.00
    俘
    1.00
     matériaux
    1.00
     écout
    0.99
     prédé
    0.98
     hés
    0.97
    Activations Density 0.007%

    No Known Activations