Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8303
    Prev
    Next
    INDEX
    Explanations

    squash PSA

    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
     Rocking
    -0.77
    вач
    -0.74
    avais
    -0.72
    レース
    -0.70
    grandes
    -0.69
    zzling
    -0.69
     yên
    -0.68
     auricular
    -0.68
     Forming
    -0.67
     棒
    -0.67
    POSITIVE LOGITS
     PSA
    1.48
     squash
    1.28
     Squash
    1.23
    PSA
    1.22
    squ
    0.99
    Squ
    0.93
     SQU
    0.90
     psa
    0.88
     Professional
    0.83
     AssemblyCompany
    0.83
    Activations Density 0.014%

    No Known Activations