© 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. 258531
    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
    可
    0.51
    (
    0.48
    분이
    0.45
    （
    0.45
     (
    0.42
    ↵↵
    0.42
     Targets
    0.42
    ↵↵↵↵
    0.41
     to
    0.40
     accomplishments
    0.40
    POSITIVE LOGITS
     сцен
    0.61
     scène
    0.55
     мор
    0.55
     આવ
    0.54
     സ്റ്റ
    0.53
     скри
    0.53
     космети
    0.53
    䣮
    0.52
     הס
    0.51
    rzym
    0.51
    Activations Density 0.001%

    No Known Activations