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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118906
    Prev
    Next
    INDEX
    Explanations

    cell lines

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

    names of cell lines (like PC12, HT-29, HEP3B) in scientific research 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_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
     primary
    -0.77
     HE
    -0.76
    nik
    -0.74
     動
    -0.71
    Contrato
    -0.71
     Primary
    -0.69
     impeccable
    -0.68
    prime
    -0.68
    områ
    -0.68
    icom
    -0.67
    POSITIVE LOGITS
     cells
    1.65
     cell
    1.40
     lines
    1.24
     line
    1.21
     línea
    1.08
    cells
    1.00
    Cells
    0.98
     líneas
    0.96
     Cells
    0.96
     human
    0.94
    Activations Density 0.233%

    No Known Activations