© 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. 225548
    Prev
    Next
    INDEX
    Explanations

    exponential linear unit

    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
     consta
    0.48
     พิจ
    0.46
     принято
    0.46
     Mith
    0.45
     вед
    0.45
    Jy
    0.45
     একবার
    0.44
     ប
    0.44
     провод
    0.44
     масштаб
    0.44
    POSITIVE LOGITS
     leven
    0.44
     ANYTHING
    0.44
    γων
    0.44
    ꯦ
    0.43
    ellini
    0.42
    itlement
    0.42
    ͈
    0.42
    urre
    0.41
    数据显示
    0.40
    딴
    0.40
    Activations Density 0.001%

    No Known Activations