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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8489
    Prev
    Next
    INDEX
    Explanations

    code formatting and declarations

    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_34/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
     पनि
    -0.89
     imaginar
    -0.84
    Má
    -0.77
    ỏi
    -0.77
    ссора
    -0.77
    틱
    -0.76
    Hashtable
    -0.74
     Yon
    -0.73
    дента
    -0.73
     liczba
    -0.72
    POSITIVE LOGITS
     pož
    0.85
    Via
    0.79
    /**
    0.79
    okhttp
    0.77
     außen
    0.77
    strual
    0.76
    erie
    0.74
    西哥
    0.71
    çalves
    0.71
    ckeye
    0.70
    Activations Density 0.022%

    No Known Activations