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. 8384
    Prev
    Next
    INDEX
    Explanations

    constant ongoing action

    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
     langsung
    -0.92
     then
    -0.83
    ذهب
    -0.74
    México
    -0.73
     subito
    -0.73
    Verse
    -0.73
    ባ
    -0.72
    cti
    -0.72
     presión
    -0.72
    EIP
    -0.71
    POSITIVE LOGITS
     constantly
    1.45
     постоянно
    1.20
     continually
    1.20
     CONSTANT
    1.11
     continuously
    1.09
     nonstop
    1.08
     Gradually
    1.05
    constant
    1.05
     ständig
    1.00
    Gradu
    0.99
    Activations Density 0.005%

    No Known Activations