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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8555
    Prev
    Next
    INDEX
    Explanations

    reserves and stores

    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
    Lindsey
    -0.81
    ieš
    -0.78
     conscientes
    -0.77
    孢
    -0.76
    lectricité
    -0.75
    iksa
    -0.75
    ajemy
    -0.74
     lógico
    -0.73
    cinfo
    -0.73
    logIn
    -0.72
    POSITIVE LOGITS
     reserves
    4.38
     reserve
    3.39
     Reserves
    2.83
     stocks
    2.69
    reserve
    2.66
     stored
    2.53
     ذخ
    2.50
     stock
    2.47
     stores
    2.45
     reservas
    2.44
    Activations Density 0.089%

    No Known Activations