© 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. 237168
    Prev
    Next
    INDEX
    Explanations

    factors such as

    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
    number
    0.47
     מספר
    0.47
     исти
    0.47
     Список
    0.46
     গুপ্ত
    0.46
     నమోదు
    0.46
     ប
    0.45
    Pergunta
    0.45
    之一
    0.45
     様
    0.45
    POSITIVE LOGITS
     refreshment
    0.51
     hairst
    0.49
     glider
    0.47
     recreational
    0.46
     CTC
    0.46
     playtime
    0.46
     pastoral
    0.44
     glacial
    0.44
     bittersweet
    0.44
     distanciation
    0.44
    Activations Density 0.001%

    No Known Activations