© 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. 54154
    Prev
    Next
    INDEX
    Explanations

    time duration

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

    language and academic topics

    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
    ối
    0.48
    Aux
    0.48
    渶
    0.45
    Baş
    0.45
    iness
    0.45
    到
    0.45
     adalah
    0.44
    的最大
    0.44
    maximal
    0.44
    ي
    0.43
    POSITIVE LOGITS
     কৌশ
    0.46
     системи
    0.45
     чтоб
    0.45
     hänen
    0.44
     pręd
    0.44
    υτό
    0.44
    수를
    0.42
    ান্ত্রিক
    0.42
     geologic
    0.42
     curric
    0.41
    Activations Density 0.001%

    No Known Activations