© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4289
    Prev
    Next
    INDEX
    Explanations

    python code blocks

    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_40_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
     ອ
    0.38
     বাক্য
    0.34
     számára
    0.33
     trow
    0.33
    ḧ
    0.32
     ஆண
    0.32
     текст
    0.32
    懺
    0.32
    ansson
    0.31
     vattati
    0.31
    POSITIVE LOGITS
    python
    0.41
     Python
    0.39
    Python
    0.39
     PYTHON
    0.37
    PYTHON
    0.34
     python
    0.34
    group
    0.31
    送料無料
    0.31
    чені
    0.30
    に関
    0.30
    Activations Density 0.000%

    No Known Activations