© 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. 257793
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    lu
    0.47
     ል
    0.46
    ︹
    0.45
    manifolds
    0.44
     ivvu
    0.43
    SIR
    0.43
    !!)
    0.43
    Planner
    0.43
     Planner
    0.42
    🏦
    0.42
    POSITIVE LOGITS
     heme
    0.47
     opaque
    0.45
    ли
    0.43
     aut
    0.43
     oxygen
    0.43
    ссии
    0.43
     thermos
    0.42
    пии
    0.42
     monochromatic
    0.42
     selves
    0.41
    Activations Density 0.002%

    No Known Activations