© 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. 90221
    Prev
    Next
    INDEX
    Explanations

    writing statements or information

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

    lists of items and their implications for decisions or structure

    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
     cárc
    0.54
    farmers
    0.50
    ポケモン
    0.47
    ík
    0.46
     insectes
    0.45
     軍
    0.45
    farmer
    0.44
    cx
    0.42
     Mitte
    0.42
     جیل
    0.42
    POSITIVE LOGITS
     Multiply
    0.45
    ارا
    0.41
     Ö
    0.41
    сив
    0.41
     โอ้
    0.41
    觅
    0.41
    RUNTIME
    0.41
     riječi
    0.41
    赠
    0.41
    涮
    0.41
    Activations Density 0.000%

    No Known Activations