© 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. 255349
    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
    hell
    0.45
    ="
    0.44
    看出
    0.43
    태
    0.43
    Mark
    0.43
    াচ্ছে
    0.43
    isk
    0.43
    ҳ
    0.43
    αι
    0.42
    ç
    0.42
    POSITIVE LOGITS
    VICIO
    0.56
     besonderen
    0.54
     envoyer
    0.53
     arbe
    0.52
    evento
    0.51
    QUESTIONS
    0.49
     feme
    0.49
     pendapatan
    0.48
     estím
    0.48
     asistencia
    0.46
    Activations Density 0.003%

    No Known Activations