© 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. 252276
    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
    很
    0.53
    那边
    0.48
     virtuel
    0.47
     sido
    0.47
    也是
    0.46
    的
    0.46
     been
    0.45
    一般的
    0.45
    在
    0.45
     Freeway
    0.44
    POSITIVE LOGITS
     세포
    0.50
     कैश
    0.46
     Ар
    0.46
     клетки
    0.45
    sentence
    0.45
    фона
    0.45
     нормы
    0.44
    вар
    0.44
    िकेट
    0.44
     항
    0.44
    Activations Density 0.002%

    No Known Activations