© 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. 12302
    Prev
    Next
    INDEX
    Explanations

    indexing `i`

    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
    junta
    -1.10
     only
    -1.00
     use
    -0.97
    ったので
    -0.96
    笘
    -0.95
     and
    -0.94
    ducati
    -0.93
    lerinden
    -0.93
     are
    -0.92
     silahkan
    -0.92
    POSITIVE LOGITS
    
    1.02
     presenti
    0.91
    （※
    0.91
    Fortunately
    0.91
    ніх
    0.90
    Kommentare
    0.89
    画像は
    0.87
     Valerio
    0.87
     éx
    0.86
    Considering
    0.85
    Activations Density 0.003%

    No Known Activations