© 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. 12224
    Prev
    Next
    INDEX
    Explanations

    second or third place

    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
     Offisielt
    -1.02
     題
    -1.01
     आधार
    -0.94
     When
    -0.93
    了
    -0.92
    kelen
    -0.91
    ıld
    -0.90
    每年
    -0.89
     Combine
    -0.88
     its
    -0.88
    POSITIVE LOGITS
     moest
    1.15
     insectos
    1.09
     another
    1.09
     third
    1.05
     adelantado
    0.99
     jette
    0.94
    同じく
    0.93
    ῖς
    0.92
     ایست
    0.92
     intentos
    0.90
    Activations Density 0.012%

    No Known Activations