© 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. 260494
    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
     regardless
    0.52
     brasileiro
    0.49
     incorporating
    0.47
     قرب
    0.44
     incorporates
    0.44
     большинство
    0.44
     وسط
    0.43
    挟
    0.43
    കൻ
    0.43
     سرب
    0.43
    POSITIVE LOGITS
    ข
    0.54
    đ
    0.48
    ปล
    0.47
     gái
    0.47
    赋
    0.47
    ड्रा
    0.44
    াক
    0.44
     plaisir
    0.43
     felicidad
    0.43
    ﻟ
    0.43
    Activations Density 0.000%

    No Known Activations