© 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. 18464
    Prev
    Next
    INDEX
    Explanations

    conjunctions and sentence starters

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

    further detail

    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
    political
    0.51
    қ
    0.48
    σωπ
    0.46
     fără
    0.46
     včetně
    0.46
    ев
    0.44
    ENTY
    0.44
    노
    0.43
    اف
    0.42
    토
    0.42
    POSITIVE LOGITS
    接下來
    0.92
    接下来
    0.92
    还有一个
    0.79
     আরেকটি
    0.79
    那我們
    0.78
     அடுத்து
    0.76
     further
    0.72
    さて
    0.72
     maintenant
    0.72
     মজার
    0.72
    Activations Density 0.080%

    No Known Activations