© 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. 108547
    Prev
    Next
    INDEX
    Explanations

    categorizing involvement and conditions

    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
     设计
    0.46
    𝐍
    0.43
    nson
    0.42
     गीत
    0.42
    pleClass
    0.41
     Accuracy
    0.41
     Современ
    0.41
    藓
    0.41
    悆
    0.41
    Representative
    0.40
    POSITIVE LOGITS
    、
    0.62
     stomach
    0.57
     worse
    0.55
     sintomas
    0.54
     plummeted
    0.52
     peor
    0.51
     crumpled
    0.51
     pungent
    0.50
     intramuscular
    0.50
     pellets
    0.48
    Activations Density 0.009%

    No Known Activations