© 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. 22-GEMMASCOPE-RES-131K
    4. 11477
    Prev
    Next
    INDEX
    Explanations

    place names and institutions

    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
    】
    -1.06
     kinda
    -1.02
     actually
    -1.01
     either
    -0.99
    red
    -0.94
     alone
    -0.93
     ampio
    -0.91
     instead
    -0.90
    都
    -0.89
     possibilities
    -0.89
    POSITIVE LOGITS
     in
    1.73
     Suomessa
    1.16
    嵯
    1.04
    🧼
    1.00
    つづく
    1.00
    petits
    0.99
    lumber
    0.98
    Mish
    0.98
    薮
    0.96
    nál
    0.93
    Activations Density 0.148%

    No Known Activations