© 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. 65361
    Prev
    Next
    INDEX
    Explanations

    non-English characters

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

    documentation

    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
    
    0.58
    ár
    0.57
    ab
    0.54
    do
    0.53
    ple
    0.52
    ili
    0.52
    iko
    0.52
    ih
    0.51
    lem
    0.51
    ande
    0.50
    POSITIVE LOGITS
    옻
    0.48
     INDIA
    0.47
    オイル
    0.47
    யா
    0.46
    สะดวก
    0.46
    रातील
    0.45
     zašt
    0.45
    ড়াল
    0.45
    MIER
    0.45
     CIN
    0.44
    Activations Density 0.000%

    No Known Activations