© 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. 211321
    Prev
    Next
    INDEX
    Explanations

    transport fueldamaged enamelrent backis 1

    np_acts-logits-general · gemini-2.5-flash-lite

    image recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     falando
    0.45
    👾
    0.44
    社長
    0.44
     literalmente
    0.43
     पेशे
    0.43
    レクトリ
    0.43
     seman
    0.43
     fárm
    0.43
     اگر
    0.42
     நிர
    0.42
    POSITIVE LOGITS
    s
    0.51
     Lantern
    0.49
     assemblies
    0.46
     decency
    0.44
    定义
    0.44
     popularity
    0.43
     Forms
    0.42
     Route
    0.41
     Jetty
    0.41
     epistle
    0.41
    Activations Density 0.000%

    No Known Activations