© 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. 249143
    Prev
    Next
    INDEX
    Explanations

    Persian textiles

    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
    यूपी
    0.52
    NEY
    0.49
    Bi
    0.48
    WATER
    0.48
    V
    0.48
    LP
    0.46
    LF
    0.46
    hi
    0.45
    高
    0.45
    KA
    0.44
    POSITIVE LOGITS
    荩
    0.49
     spheres
    0.48
     remod
    0.47
     Doremi
    0.47
     რა
    0.46
     tombol
    0.46
     fairytale
    0.45
     textile
    0.45
     safeguarding
    0.45
     textiles
    0.45
    Activations Density 0.001%

    No Known Activations