© 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. 258958
    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
     votes
    0.54
    )
    0.54
     drinking
    0.53
     evaluated
    0.52
     spitting
    0.49
    ม
    0.49
     sucking
    0.48
     relevance
    0.48
    .]
    0.46
     where
    0.46
    POSITIVE LOGITS
     ημέ
    0.50
     მარ
    0.48
    algebras
    0.48
     গ্রন্থের
    0.48
     中心
    0.47
     保護
    0.47
     दम
    0.46
     విభ
    0.46
     しっかり
    0.46
    oprote
    0.46
    Activations Density 0.000%

    No Known Activations