© 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. 34-GEMMASCOPE-RES-131K
    7. 75698
    Prev
    Next
    INDEX
    Explanations

    news datelines and scientific names

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

    news article formatting, particularly bylines, datelines, and article structure.

    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_34/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
     лук
    -0.86
    omitempty
    -0.82
     非
    -0.79
     sorgen
    -0.79
     ades
    -0.77
    淺
    -0.76
    melse
    -0.73
     asig
    -0.73
     elde
    -0.73
     Fel
    -0.73
    POSITIVE LOGITS
     ANI
    1.18
    ANI
    1.02
    ेड
    0.84
     Sputnik
    0.80
    escolar
    0.79
     approfon
    0.79
    ربية
    0.78
     پرداز
    0.76
    órias
    0.76
     Lymph
    0.73
    Activations Density 0.009%

    No Known Activations