© 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. 82453
    Prev
    Next
    INDEX
    Explanations

    polytope, genomes, script, config

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

    numeric values, especially years or version numbers in technical and reference documents.

    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
    LAN
    -0.77
    гите
    -0.74
    ñar
    -0.74
     DAMAGES
    -0.73
    lify
    -0.71
    york
    -0.70
    точка
    -0.70
     Diretto
    -0.69
     SCIENCES
    -0.69
    correct
    -0.68
    POSITIVE LOGITS
    Dusk
    0.69
     intermedio
    0.68
    Lop
    0.66
     reclu
    0.65
     Scrip
    0.65
     vient
    0.65
     👏
    0.63
     знак
    0.61
    Provision
    0.60
    ȍ
    0.60
    Activations Density 0.068%

    No Known Activations