© 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. 6936
    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
    getColumn
    0.59
    طق
    0.54
     teorie
    0.54
    Kelly
    0.53
    ερ
    0.53
    맺
    0.53
    Other
    0.51
    Julie
    0.51
    носи
    0.51
     teoría
    0.51
    POSITIVE LOGITS
    (
    0.47
     Int
    0.42
     distributes
    0.42
    ivum
    0.41
    ulph
    0.40
     FAC
    0.39
     copolymer
    0.39
     Berliner
    0.39
     dehydrogen
    0.39
     gegen
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.