© 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. 53238
    Prev
    Next
    INDEX
    Explanations

    initialize programming constructs

    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
    racción
    0.49
     एजु
    0.45
    न्तु
    0.45
     iglesia
    0.44
    पति
    0.44
    ේ
    0.44
    상이
    0.43
    원이
    0.43
    posaż
    0.43
    杣
    0.43
    POSITIVE LOGITS
    etre
    0.50
    ive
    0.46
     unambiguous
    0.46
    uk
    0.46
    ak
    0.45
    et
    0.45
     sign
    0.44
     signature
    0.44
    '
    0.44
     Ukrainian
    0.44
    Activations Density 0.001%

    No Known Activations