© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116070
    Prev
    Next
    INDEX
    Explanations

    holotype or type specimen

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

    type specimens in scientific taxonomic descriptions, particularly focusing on the holotype or type species of biological 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
     ಶ
    -0.79
    がよく
    -0.77
    farol
    -0.76
     selama
    -0.73
     unsus
    -0.72
    faccia
    -0.71
    hibli
    -0.71
    wilson
    -0.70
    hrer
    -0.70
     ресни
    -0.70
    POSITIVE LOGITS
     holotype
    1.72
     type
    1.53
    holo
    1.42
    Type
    1.33
    type
    1.28
    otype
    1.27
     Type
    1.24
    タイプ
    1.23
     Holo
    1.22
    TYPE
    1.20
    Activations Density 0.046%

    No Known Activations