© 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. 255155
    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
     similarly
    0.40
     предше
    0.40
     memoranda
    0.38
     appended
    0.38
     επίσης
    0.37
     also
    0.36
    (−
    0.36
     preceded
    0.36
    −
    0.36
     ArrayRef
    0.36
    POSITIVE LOGITS
     lidí
    0.51
     peau
    0.50
    כל
    0.49
     ludzi
    0.47
     खुशी
    0.47
     ל
    0.46
    することで
    0.46
    hungry
    0.45
     dafür
    0.44
     někol
    0.44
    Activations Density 0.002%

    No Known Activations