© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66696
    Prev
    Next
    INDEX
    Explanations

    scientific and common names

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

    scientific names of species in biological/taxonomic 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_22/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
     miſ
    -1.73
    viembre
    -1.66
    VideoView
    -1.66
    ૉ
    -1.57
     filós
    -1.55
     garansi
    -1.45
     maail
    -1.45
    бѣ
    -1.41
     discípulos
    -1.39
     Inſ
    -1.39
    POSITIVE LOGITS
     ویتامین
    1.59
    Filmography
    1.34
    暧
    1.30
     pidana
    1.26
    อร่อย
    1.24
     کرت
    1.18
    离婚
    1.16
    Tottenham
    1.15
    atigable
    1.15
     别墅
    1.14
    Activations Density 0.010%

    No Known Activations