© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110573
    Prev
    Next
    INDEX
    Explanations

    list formatting and delimiters

    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
     when
    -0.86
     after
    -0.84
     combines
    -0.77
    交渉
    -0.77
    http
    -0.76
     all
    -0.76
     IN
    -0.76
     because
    -0.75
     mainly
    -0.75
     not
    -0.74
    POSITIVE LOGITS
    Etape
    0.95
    苏联
    0.94
     įva
    0.91
     richiede
    0.90
    Problema
    0.90
     takiej
    0.88
    Politique
    0.88
     diinginkan
    0.87
     Krzysztof
    0.87
    Étape
    0.87
    Activations Density 0.007%

    No Known Activations