© 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. 260591
    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
    íamos
    0.56
    ек
    0.55
    ゲ
    0.54
     laborales
    0.50
    કિંગ
    0.50
     мотива
    0.49
     entornos
    0.48
    eraient
    0.47
     характеристи
    0.47
    фе
    0.46
    POSITIVE LOGITS
    ↵↵
    0.49
     Regional
    0.49
    entropy
    0.47
     Upper
    0.46
    Token
    0.46
     Astronomical
    0.45
     Badan
    0.44
    Upper
    0.44
    Regional
    0.44
     Simult
    0.43
    Activations Density 0.001%

    No Known Activations