© 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. 60058
    Prev
    Next
    INDEX
    Explanations

    is that

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

    initial connection

    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
     actitudes
    0.51
     distrust
    0.48
    installed
    0.46
     Khmer
    0.45
    신
    0.45
     내용을
    0.45
    ovým
    0.45
     विशेषताओं
    0.44
    我现在
    0.44
    手臂
    0.44
    POSITIVE LOGITS
     প্য
    0.42
     Yahoo
    0.41
     代
    0.41
    FAQs
    0.40
     時間
    0.40
     yahoo
    0.39
     экспеди
    0.38
     economical
    0.38
    ECON
    0.38
    錯
    0.38
    Activations Density 0.000%

    No Known Activations