© 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. 128553
    Prev
    Next
    INDEX
    Explanations

    biological and medical terms

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

    biological organism names, particularly insects and parasites.

    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
     boneca
    -1.98
    adaş
    -1.96
     humanidade
    -1.95
     nuvem
    -1.95
     limpieza
    -1.95
    鵟
    -1.95
    苦手な
    -1.95
     interwoven
    -1.94
     bandeira
    -1.92
     visites
    -1.91
    POSITIVE LOGITS
    there
    2.09
     and
    2.06
    2.02
    <i>
    2.00
    we
    1.89
    我们要
    1.79
     イラストレーション
    1.78
    me
    1.77
            
    1.77
    k
    1.76
    Activations Density 0.009%

    No Known Activations