© 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. 26333
    Prev
    Next
    INDEX
    Explanations

    locations and scope

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

    information from sources

    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
    Meth
    0.39
    KQ
    0.39
    notepad
    0.39
    狐
    0.39
    Clipboard
    0.38
    कायदा
    0.38
     पुराना
    0.37
    Weekday
    0.37
    蓼
    0.37
    Mm
    0.37
    POSITIVE LOGITS
     parli
    0.43
     çeşit
    0.43
     fals
    0.41
    种类
    0.40
     Naj
    0.40
     Technological
    0.39
     کشورهای
    0.39
     marcas
    0.39
     technolog
    0.38
     svoje
    0.38
    Activations Density 0.001%

    No Known Activations