© 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. 22-GEMMASCOPE-RES-131K
    7. 11540
    Prev
    Next
    INDEX
    Explanations

    small, limited, or scarce

    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_22/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
    ongeza
    -1.03
     myös
    -0.99
    gewiesen
    -0.96
     havet
    -0.95
     sekä
    -0.94
     також
    -0.93
    hichever
    -0.93
     olika
    -0.93
     dsg
    -0.93
     فاض
    -0.92
    POSITIVE LOGITS
     only
    1.80
     barely
    1.70
     hardly
    1.61
     apenas
    1.52
     less
    1.40
     mostly
    1.35
     no
    1.28
     (<
    1.27
     mainly
    1.16
     scarcely
    1.13
    Activations Density 0.109%

    No Known Activations