© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    create and develop new things

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

    creating new things

    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
     材質
    0.20
    を使用
    0.19
     ）
    0.19
    ）。
    0.18
     vorhand
    0.18
    <unused2128>
    0.18
     এছাড়া
    0.17
     Ancak
    0.17
     இயக்கு
    0.17
    ngth
    0.17
    POSITIVE LOGITS
     a
    0.29
     an
    0.25
     charlas
    0.22
    一个小
    0.21
     recomendaciones
    0.21
    a
    0.21
    一个新的
    0.21
    了自己的
    0.21
     sebuah
    0.21
     nuevas
    0.21
    Activations Density 0.790%

    No Known Activations