© 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. 36821
    Prev
    Next
    INDEX
    Explanations

    linked by

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

    connected to, capacity for

    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
     diput
    0.52
    ៏
    0.51
     आजा
    0.46
     compléter
    0.46
     bikin
    0.46
     skr
    0.46
     resul
    0.46
     tailored
    0.46
     billboard
    0.45
     उ
    0.45
    POSITIVE LOGITS
    حال
    0.45
    אי
    0.44
    Started
    0.43
    মাত্রা
    0.43
    কাজ
    0.43
    コーヒー
    0.43
    藿
    0.42
    رل
    0.42
    ANNOT
    0.42
    عم
    0.41
    Activations Density 0.000%

    No Known Activations