© 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. 11546
    Prev
    Next
    INDEX
    Explanations

    Risk factors, Call of Duty, Personality predictor

    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
     Produkte
    -1.17
     jegy
    -1.02
     prodotti
    -0.97
     termé
    -0.93
    Tentang
    -0.92
    Kelebihan
    -0.92
     黑色
    -0.91
    Spesifikasi
    -0.91
     альбом
    -0.90
    Tob
    -0.89
    POSITIVE LOGITS
     предыду
    0.87
    ースター
    0.84
    delen
    0.84
     like
    0.80
     höl
    0.78
    =$_
    0.77
    有一定的
    0.77
     wooden
    0.77
    部に
    0.76
    Ǵ
    0.76
    Activations Density 0.002%

    No Known Activations