© 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. 191559
    Prev
    Next
    INDEX
    Explanations

    Calling the

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

    insurance or flip flops

    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
    ッチン
    0.58
    ूटूथ
    0.54
    იც
    0.52
     সম্মতি
    0.52
    י
    0.52
    事前に
    0.51
    <unused467>
    0.50
    JScripts
    0.50
    াহিয়া
    0.49
     escort
    0.49
    POSITIVE LOGITS
    0
    0.49
    iloc
    0.47
    iede
    0.45
     positioned
    0.45
    ida
    0.45
     M
    0.45
    ce
    0.45
    Lay
    0.43
    ke
    0.43
     V
    0.42
    Activations Density 0.001%

    No Known Activations