© 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. 255850
    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
    вут
    0.46
    ଛ
    0.46
    ƅ
    0.45
    委員
    0.45
     вели
    0.45
     США
    0.45
     বিয়ে
    0.44
    絟
    0.43
     condivid
    0.42
    स्तान
    0.42
    POSITIVE LOGITS
    ä
    0.53
    ub
    0.51
     of
    0.48
    ريبة
    0.45
     was
    0.43
    াধিক
    0.43
    akon
    0.43
    ("~/
    0.43
    RA
    0.42
     Phantom
    0.42
    Activations Density 0.000%

    No Known Activations