© 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. 34-GEMMASCOPE-RES-131K
    7. 31392
    Prev
    Next
    INDEX
    Explanations

    specimens and collections

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

    scientific texts discussing biological specimens and their collections, particularly focused on taxonomic information and museum specimens.

    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
     keç
    -0.84
    ctory
    -0.82
    subtree
    -0.76
    pollution
    -0.75
    埜
    -0.74
    ὡ
    -0.73
    小松
    -0.73
    Chooser
    -0.73
    ➍
    -0.73
     Translation
    -0.72
    POSITIVE LOGITS
     specimens
    2.84
     collections
    2.59
     specimen
    2.42
     collection
    2.27
     Specimens
    2.14
     museum
    2.08
     Collections
    2.02
    Collections
    2.00
    collection
    1.99
    collections
    1.99
    Activations Density 0.067%

    No Known Activations