© 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. 260060
    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
     scrivere
    0.59
    ć
    0.53
     correcta
    0.52
     escribir
    0.51
    intahan
    0.49
    playSound
    0.49
     लीटर
    0.48
     спі
    0.48
     correctes
    0.48
     valori
    0.48
    POSITIVE LOGITS
    背
    0.50
    ိမ်
    0.48
    ال
    0.47
    AT
    0.47
    ON
    0.47
    先
    0.47
    Wave
    0.46
     bows
    0.46
    ेश्च
    0.46
    
    0.45
    Activations Density 0.001%

    No Known Activations