© 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. 21781
    Prev
    Next
    INDEX
    Explanations

    lost sheep, lost coin

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

    not choosing to

    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
     nymphs
    0.44
     συμμε
    0.41
     বিভিন্ন
    0.40
     فى
    0.40
    ▶
    0.39
     vervolgens
    0.38
     participan
    0.38
     competing
    0.38
    各类
    0.38
    وفي
    0.38
    POSITIVE LOGITS
     BECAUSE
    0.52
     wouldn
    0.51
    ullo
    0.45
     çünkü
    0.44
    ý
    0.43
    क्योंकि
    0.42
     नहीं
    0.41
     isang
    0.41
     someday
    0.41
    ši
    0.41
    Activations Density 0.002%

    No Known Activations