Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11756
    Prev
    Next
    INDEX
    Explanations

    Pakistan and Pakistani national references

    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
    ࿙
    -2.41
    ?
    -2.08
     we
    -2.05
     have
    -1.88
     altogether
    -1.77
     monstrous
    -1.75
     todavía
    -1.74
    明天
    -1.73
    未必
    -1.73
     новая
    -1.73
    POSITIVE LOGITS
    鉭
    2.30
     手绘
    2.16
     думать
    2.14
    /////////////
    2.03
    //////
    2.02
    ar
    2.00
     ибо
    1.98
    毟
    1.98
    ///////
    1.92
    /////////
    1.91
    Activations Density 0.008%

    No Known Activations