© 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. 28551
    Prev
    Next
    INDEX
    Explanations

    unsettling outcomes

    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
     thinkers
    0.54
    之後
    0.47
    眾
    0.43
     teachers
    0.43
    認知
    0.43
    ---
    0.43
     punten
    0.42
    坸
    0.42
     एक्ट्रेस
    0.41
     Noch
    0.41
    POSITIVE LOGITS
    inį
    0.47
     охла
    0.46
    ného
    0.43
    ਿੱ
    0.42
     chilled
    0.42
     ενός
    0.42
    olesale
    0.41
     suitably
    0.41
    ewną
    0.39
     લગભગ
    0.39
    Activations Density 0.001%

    No Known Activations