© 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. 34-GEMMASCOPE-RES-131K
    7. 92525
    Prev
    Next
    INDEX
    Explanations

    karyometry, aim, development, background

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

    academic or scholarly text formatting, particularly in research articles and papers.

    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
    🚫
    -0.79
    iteter
    -0.75
    brainly
    -0.74
     совмест
    -0.74
     fortunate
    -0.73
    ❌
    -0.73
    ينو
    -0.73
    entraî
    -0.71
     ۹
    -0.71
    驚く
    -0.69
    POSITIVE LOGITS
     DOI
    0.98
    DOI
    0.85
     handball
    0.80
     probiotics
    0.79
    ptos
    0.78
    segs
    0.78
    .　
    0.77
     applicator
    0.77
    cedores
    0.76
     мы
    0.76
    Activations Density 0.008%

    No Known Activations