© 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. 138201
    Prev
    Next
    INDEX
    Explanations

    regarding the

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

    string manipulation

    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
     ស
    0.52
    ﺔ
    0.50
     وك
    0.50
     처
    0.49
     则
    0.49
     تسه
    0.49
    讀
    0.46
     पत्र
    0.46
    nn
    0.46
    類
    0.46
    POSITIVE LOGITS
     swirling
    0.50
     stocked
    0.48
    at
    0.47
    on
    0.46
    stocked
    0.46
     scented
    0.46
    lycerin
    0.46
    ビア
    0.45
     adrift
    0.43
    assium
    0.43
    Activations Density 0.001%

    No Known Activations