© 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. 252929
    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
    峎
    0.50
     Havana
    0.50
     I
    0.49
     Approximate
    0.47
     WILSON
    0.46
    ﮔ
    0.46
    變得
    0.46
    理念
    0.45
     Príncipe
    0.45
    這是
    0.44
    POSITIVE LOGITS
     pathos
    0.54
     qualit
    0.51
     surm
    0.50
    esi
    0.49
    engl
    0.48
     loud
    0.48
    a
    0.48
    loud
    0.47
     nem
    0.47
    yum
    0.46
    Activations Density 0.000%

    No Known Activations