© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109156
    Prev
    Next
    INDEX
    Explanations

    abdominal pain and obesity

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

    words related to parts of the body, particularly the abdominal region.

    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
    乆
    -0.85
    łow
    -0.83
     风格
    -0.81
     SEGU
    -0.81
    アレル
    -0.81
     字体
    -0.79
    にん
    -0.77
     breasted
    -0.77
    皲
    -0.77
     改
    -0.76
    POSITIVE LOGITS
     cavity
    0.99
    button
    0.96
    dancer
    0.90
    Belly
    0.90
     speaker
    0.89
     button
    0.87
     dancer
    0.87
     dancers
    0.83
    acke
    0.82
     мона
    0.81
    Activations Density 0.016%

    No Known Activations