© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8265
    Prev
    Next
    INDEX
    Explanations

    ecology

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

    the word "ecology" or references to ecological studies.

    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
    '
    -3.55
     Their
    -2.58
    亟
    -2.44
    先是
    -2.36
    ).
    -2.33
     replete
    -2.23
    佯
    -2.19
     […]
    -2.16
     portraying
    -2.14
     creando
    -2.06
    POSITIVE LOGITS
    𖡼
    2.78
    錀
    2.44
     мою
    2.41
    0
    2.33
     pikir
    2.33
    and
    2.31
     orari
    2.30
    i
    2.30
     hasilnya
    2.20
    
    2.20
    Activations Density 0.003%

    No Known Activations