© 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. 11405
    Prev
    Next
    INDEX
    Explanations

    counting ordinal numbers

    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
     about
    -0.92
     zubehör
    -0.88
    weza
    -0.87
     privacidade
    -0.87
     amea
    -0.85
    らなかった
    -0.84
    <0x80>
    -0.84
     pâtes
    -0.83
    ایب
    -0.81
     wied
    -0.81
    POSITIVE LOGITS
     or
    1.09
    
    0.97
     byg
    0.94
    ánica
    0.93
    arska
    0.93
    小行星
    0.92
    +#+#
    0.91
     tango
    0.91
    켓
    0.90
    ribution
    0.90
    Activations Density 0.025%

    No Known Activations