© 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. 254926
    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
     Lorem
    0.50
    า
    0.49
    IN
    0.48
    <0x80>
    0.48
    FEDERAL
    0.47
    M
    0.46
    <0x9C>
    0.46
     GRAY
    0.46
    ल्ल्या
    0.45
     FEDERAL
    0.45
    POSITIVE LOGITS
    נ
    0.52
    دور
    0.48
    äch
    0.46
     alltid
    0.46
     subsidies
    0.45
     incor
    0.44
    كون
    0.44
     organise
    0.44
     despite
    0.43
    institutional
    0.43
    Activations Density 0.000%

    No Known Activations