© 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. 195916
    Prev
    Next
    INDEX
    Explanations

    foreign language indicators

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

    Genetics, Sustainability, Dynamics, testing framework

    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
    ラ
    0.48
    न्ति
    0.47
    ო
    0.46
    לו
    0.46
    या
    0.45
    לב
    0.45
     impost
    0.45
    نے
    0.44
     pade
    0.44
    帝
    0.43
    POSITIVE LOGITS
     въ
    0.54
     पूर्
    0.53
    jesi
    0.49
     медицин
    0.48
     э
    0.48
     стек
    0.48
     расчет
    0.48
     совет
    0.47
    grunt
    0.46
     মাতৃ
    0.46
    Activations Density 0.000%

    No Known Activations