© 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. 221593
    Prev
    Next
    INDEX
    Explanations

    additional pay

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

    Grid transposition

    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
    ینگ
    0.49
    вети
    0.47
    ور
    0.47
    াদে
    0.46
    砧
    0.46
    Мі
    0.46
    ፈል
    0.46
    تن
    0.46
     migrations
    0.45
    arrivals
    0.45
    POSITIVE LOGITS
    {(-
    0.48
     Podczas
    0.46
    ii
    0.45
    kom
    0.44
    zw
    0.44
     swapping
    0.43
     podczas
    0.43
    ၇
    0.42
    TaskPojo
    0.41
    ၀၀
    0.41
    Activations Density 0.000%

    No Known Activations