© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118978
    Prev
    Next
    INDEX
    Explanations

    tables, lists, or code blocks

    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
     while
    -1.11
     because
    -1.07
     mostly
    -1.05
     considerably
    -1.02
     getting
    -1.00
     solely
    -1.00
     noticeable
    -0.96
     virtually
    -0.95
     in
    -0.94
     more
    -0.94
    POSITIVE LOGITS
     две
    0.97
     trzec
    0.95
    🫴
    0.92
     trois
    0.90
     três
    0.86
     zwi
    0.86
    <th>
    0.84
    athon
    0.84
     dividida
    0.84
     затем
    0.83
    Activations Density 0.002%

    No Known Activations