© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 76282
    Prev
    Next
    INDEX
    Explanations

    share, years, voxel, unauthorized, injection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    میٹ
    0.47
    ﺘ
    0.47
     estabilidad
    0.46
    ټ
    0.46
    Ш
    0.46
    тия
    0.45
    тел
    0.45
    лга
    0.45
     فیصلہ
    0.44
    Inflation
    0.44
    POSITIVE LOGITS
     प्रा
    0.49
     আগ্রহ
    0.46
     пересе
    0.43
    প্রবাসী
    0.42
     perhaps
    0.42
     nhiên
    0.42
    /**
    0.41
     WITHIN
    0.41
     Freel
    0.40
     Might
    0.40
    Activations Density 0.014%

    No Known Activations