© 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. 113334
    Prev
    Next
    INDEX
    Explanations

    prey and being preyed upon

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

    the word "prey" in biological and predator-prey contexts.

    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
    ?”
    -3.52
    d
    -2.83
    …”
    -2.69
    我们就
    -2.67
    (
    -2.50
    ”?
    -2.44
    In
    -2.41
    ᜀ
    -2.39
    ”;
    -2.38
    )”
    -2.33
    POSITIVE LOGITS
     Quando
    3.11
     conocidos
    2.59
     
    2.58
    侂
    2.38
     rencont
    2.33
     在
    2.33
    
    2.23
    ㉗
    2.23
     alumínio
    2.19
     sekitar
    2.17
    Activations Density 0.001%

    No Known Activations