© 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. 12624
    Prev
    Next
    INDEX
    Explanations

    summaries and analyses

    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
    nlü
    0.46
    㖑
    0.41
    即便
    0.39
    องค์การ
    0.38
     costruito
    0.38
    飡
    0.38
     imposible
    0.38
     باسکٹ
    0.38
    少
    0.38
     அலெக்ஸாண்ட்
    0.38
    POSITIVE LOGITS
    </h2>
    0.76
    </h3>
    0.71
    </h1>
    0.57
    </h4>
    0.57
    </h5>
    0.55
     FAQs
    0.54
     Context
    0.51
     FAQ
    0.48
    Context
    0.48
     questions
    0.47
    Activations Density 0.003%

    No Known Activations