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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110376
    Prev
    Next
    INDEX
    Explanations

    month and day numbers

    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
     sebuah
    -1.20
     both
    -1.20
     també
    -1.12
     an
    -1.10
    رحلة
    -1.09
     any
    -1.06
     because
    -1.04
     throughout
    -1.04
     during
    -1.02
     业
    -1.02
    POSITIVE LOGITS
     recentemente
    1.03
     nowy
    1.02
    posted
    1.00
     moderators
    0.99
     árvore
    0.99
    sunday
    0.96
    tradu
    0.94
     солнце
    0.94
     限定
    0.93
    recently
    0.93
    Activations Density 0.013%

    No Known Activations