© 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. 260566
    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
     perturbations
    0.49
    곁
    0.45
     perturbed
    0.43
    호를
    0.42
     wrappers
    0.42
     두
    0.41
    熟悉
    0.40
     Fahrt
    0.39
     옆
    0.39
     estaban
    0.39
    POSITIVE LOGITS
    ا
    0.50
    requestFocus
    0.45
    一定要
    0.44
    ན་
    0.43
    问题
    0.43
     diritto
    0.42
    democracy
    0.42
     ആര
    0.40
     slang
    0.40
     måste
    0.40
    Activations Density 0.001%

    No Known Activations