© 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. 83065
    Prev
    Next
    INDEX
    Explanations

    proper noun followed by specific word or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     شنا
    -0.78
    듬
    -0.70
    Fuj
    -0.69
     Fuj
    -0.68
    toplasm
    -0.66
    挿
    -0.66
     причи
    -0.66
    homo
    -0.65
     opened
    -0.64
     lengths
    -0.64
    POSITIVE LOGITS
     marginal
    0.91
     grounding
    0.87
    pady
    0.86
    𝗞
    0.86
    SOFT
    0.83
    ually
    0.82
    Soft
    0.81
    ridges
    0.81
     Meilleures
    0.80
    prefixer
    0.80
    Activations Density 0.012%

    No Known Activations