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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31799
    Prev
    Next
    INDEX
    Explanations

    biological and soil samples

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

    biological fluid or sample references in scientific 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
    CIUDAD
    -0.75
     ਗ
    -0.74
    復活
    -0.72
    受伤
    -0.70
    Boxscore
    -0.69
     transportar
    -0.67
    แรก
    -0.66
     вслед
    -0.66
    Bored
    -0.66
     процес
    -0.66
    POSITIVE LOGITS
     samples
    7.13
     sample
    5.88
    samples
    5.50
     Samples
    5.13
    Samples
    5.09
    sample
    4.59
    Sample
    4.28
     SAMPLES
    4.16
     specimens
    3.94
     Sample
    3.89
    Activations Density 0.308%

    No Known Activations