© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 121721
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, or specific connectors

    np_acts-logits-general · gemini-2.5-flash-lite

    finding or following patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    0.59
    P
    0.56
    L
    0.55
    B
    0.55
    ri
    0.50
     Version
    0.50
    no
    0.50
    V
    0.50
    З
    0.50
    N
    0.49
    POSITIVE LOGITS
     vasculature
    0.57
     ہوگا۔
    0.51
    ፍ
    0.50
     profondes
    0.49
     biomarker
    0.48
     fluctuation
    0.46
    ᒎ
    0.46
     paiement
    0.45
    クー
    0.45
    ەڵ
    0.43
    Activations Density 0.006%

    No Known Activations