© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 255073
    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
    詳
    0.43
    維
    0.43
    鉄道
    0.43
    攝影
    0.42
    評
    0.41
    攤
    0.41
     میراتھن
    0.41
    皇后
    0.41
    癱
    0.41
    無法
    0.41
    POSITIVE LOGITS
     Inca
    0.49
     chois
    0.48
     recomb
    0.47
     книге
    0.46
     extiende
    0.46
     Mannes
    0.46
     extend
    0.45
     controles
    0.45
     cables
    0.45
     elegido
    0.45
    Activations Density 0.000%

    No Known Activations