© 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. 259971
    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
    درا
    0.50
    ม
    0.47
     dağı
    0.46
     sadrž
    0.45
    αυ
    0.45
    总
    0.45
     CASA
    0.44
     đem
    0.44
    夺
    0.43
     کھیلنے
    0.43
    POSITIVE LOGITS
    /**',
    0.53
    ple
    0.46
     Russians
    0.46
     Purnama
    0.45
    js
    0.44
     gone
    0.44
     ((
    0.44
     knows
    0.44
     shri
    0.43
     atoi
    0.43
    Activations Density 0.001%

    No Known Activations