© 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. 11400
    Prev
    Next
    INDEX
    Explanations

    they/their followed by actions or states

    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
     and
    -1.20
     in
    -1.02
    8
    -1.00
    uyler
    -0.99
     Möglichkeit
    -0.96
     Tätigkeit
    -0.94
    isDirectory
    -0.93
     beryllium
    -0.93
     svým
    -0.92
    anglès
    -0.91
    POSITIVE LOGITS
     Насе
    1.05
    quot
    1.02
    Bandwidth
    1.01
     PROFES
    0.99
     yhte
    0.99
    の人は
    0.98
     جميع
    0.98
     motto
    0.97
     portu
    0.97
     joked
    0.95
    Activations Density 0.022%

    No Known Activations