© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27927
    Prev
    Next
    INDEX
    Explanations

    testing frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lietuvos
    0.40
    ٦
    0.40
    ন্থা
    0.40
    DELETE
    0.39
     Lomond
    0.39
     jeweils
    0.39
    aneity
    0.39
    ヤマハ
    0.39
    侶
    0.39
    max
    0.38
    POSITIVE LOGITS
     fibrils
    0.53
     initiates
    0.47
     cells
    0.47
     moldings
    0.46
     assays
    0.44
     실행
    0.44
     filaments
    0.44
     scl
    0.44
     Inst
    0.43
     follicles
    0.43
    Activations Density 0.001%

    No Known Activations