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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8716
    Prev
    Next
    INDEX
    Explanations

    emission and its forms

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

    words and phrases related to emission or emitting of particles, light, or other outputs.

    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_10/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
    ᠂
    -2.77
    翼翼
    -2.52
    in
    -2.47
     atau
    -2.42
    身影
    -2.41
    ☫
    -2.41
     that
    -2.34
    of
    -2.33
    在你
    -2.31
     сможет
    -2.30
    POSITIVE LOGITS
     This
    2.77
    皛
    2.66
     ถ้า
    2.63
    ཫ
    2.28
     actúa
    2.28
    灩
    2.27
    ,
    2.20
    躂
    2.09
     devise
    2.08
    ︓
    2.08
    Activations Density 0.023%

    No Known Activations