© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70820
    Prev
    Next
    INDEX
    Explanations

    Turmeric, Q:, Oligolepis

    np_acts-logits-general · gemini-2.5-flash-lite

    numerical values in SVG path data or coordinate specifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     while
    -1.21
    ⌗
    -1.09
     three
    -1.06
    為に
    -1.06
     pequeñas
    -1.03
     nachher
    -1.03
    sandalias
    -1.02
     persönlich
    -1.02
     possibly
    -1.02
     these
    -1.01
    POSITIVE LOGITS
    manın
    1.23
    があります
    1.23
    も
    1.09
    Ⅳ
    1.09
    珢
    1.08
    душка
    1.08
    
    1.06
    が
    1.05
    があり
    1.04
    primarily
    1.04
    Activations Density 0.005%

    No Known Activations