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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108495
    Prev
    Next
    INDEX
    Explanations

    need financing for oxygen

    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
     ਦਿ
    0.48
     ナ
    0.46
    塭
    0.46
    蝣
    0.45
     रास्ता
    0.45
    į
    0.45
     सर्वश्रेष्ठ
    0.45
     ミ
    0.45
     細胞
    0.45
     ನೀರಿನ
    0.44
    POSITIVE LOGITS
    a
    0.48
     shipper
    0.46
    ?
    0.45
    i
    0.45
     Lister
    0.44
     acuer
    0.43
    ść
    0.42
     ros
    0.42
     L
    0.42
     Kauf
    0.41
    Activations Density 0.004%

    No Known Activations