© 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. 34-GEMMASCOPE-RES-131K
    7. 64341
    Prev
    Next
    INDEX
    Explanations

    gecko leopard boa leptin db/db <!DOCTYPEeating const

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

    scientific names and taxonomic information for animal species.

    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
    angular
    -0.91
    RV
    -0.76
    Du
    -0.73
    fil
    -0.72
    pis
    -0.71
    éli
    -0.70
    ∃
    -0.70
    лання
    -0.70
     fach
    -0.69
    حيط
    -0.69
    POSITIVE LOGITS
     pieds
    0.86
     bailout
    0.81
     het
    0.81
    gecko
    0.81
    alık
    0.78
    プロジェクト
    0.77
     jungles
    0.77
     bioactive
    0.76
    говори
    0.76
     мор
    0.76
    Activations Density 0.023%

    No Known Activations