© 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. 40-GEMMASCOPE-2-RES-262K
    7. 17526
    Prev
    Next
    INDEX
    Explanations

    German nouns ending in -ungs, -ens, -els

    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
    em
    0.47
    it
    0.46
     (
    0.46
    er
    0.46
    i
    0.44
     g
    0.42
    im
    0.41
     "
    0.41
     E
    0.40
    e
    0.39
    POSITIVE LOGITS
    完毕
    0.54
    চ্ছুক
    0.50
     څرنګ
    0.47
    期間
    0.46
     périodes
    0.45
    期间
    0.44
    қда
    0.44
     períodos
    0.41
     período
    0.41
     څرنګوالی
    0.41
    Activations Density 0.003%

    No Known Activations