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. 145
    Prev
    Next
    INDEX
    Explanations

    Citrix and citrate

    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
     Agre
    -0.81
     причин
    -0.77
    बर
    -0.77
     bolsas
    -0.75
     eligible
    -0.74
     intensa
    -0.73
     estes
    -0.72
     yorum
    -0.71
     frase
    -0.71
    isiin
    -0.70
    POSITIVE LOGITS
     cit
    1.23
     Cit
    1.16
    Cit
    1.07
     CIT
    0.88
    cit
    0.84
    CIT
    0.82
    cita
    0.81
     citrate
    0.79
     ци
    0.79
    Filename
    0.77
    Activations Density 0.041%

    No Known Activations