© 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. 10-GEMMASCOPE-RES-131K
    7. 1059
    Prev
    Next
    INDEX
    Explanations

    actor names and medical terms

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

    proper names of people, especially celebrities and actors.

    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_10/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
    '.
    -1.62
    thumbsup
    -1.51
    ',
    -1.43
    likleri
    -1.41
    кой
    -1.40
    us
    -1.38
     esquerdo
    -1.37
    ᥬ
    -1.32
     abogados
    -1.29
     outras
    -1.28
    POSITIVE LOGITS
    )=>{
    1.71
    ngOn
    1.69
     cardin
    1.63
    筇
    1.61
    栳
    1.61
    衕
    1.60
    蟶
    1.56
    Ꮌ
    1.55
    ஂ
    1.53
    謦
    1.50
    Activations Density 0.007%

    No Known Activations