© 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. 255798
    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
     neon
    0.52
    p
    0.50
    н
    0.50
     youthful
    0.47
     mothers
    0.45
     improbable
    0.45
    guru
    0.43
     timed
    0.43
     curing
    0.43
     بير
    0.43
    POSITIVE LOGITS
    しよう
    0.53
     așa
    0.51
    甃
    0.50
    劾
    0.50
    Hierarchy
    0.49
     Jop
    0.48
     Analyst
    0.48
     писать
    0.48
     ادبی
    0.48
     않았
    0.47
    Activations Density 0.000%

    No Known Activations