© 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. 253541
    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
     remettre
    0.50
     województ
    0.48
     votar
    0.48
     kq
    0.48
     aritm
    0.47
    󰡔
    0.47
     showrooms
    0.47
    лар
    0.46
    強い
    0.46
     améliorer
    0.46
    POSITIVE LOGITS
     '
    0.49
     crouching
    0.46
     diving
    0.45
     Mein
    0.44
     '*'
    0.42
     caveat
    0.42
     फील्ड
    0.42
     Meek
    0.41
     જગ
    0.39
    Cave
    0.39
    Activations Density 0.000%

    No Known Activations