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. 11779
    Prev
    Next
    INDEX
    Explanations

    Eureka! Transfer Good beer Izumi

    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
    yii
    -0.94
     uhr
    -0.90
     akurat
    -0.89
     kohdetta
    -0.88
    teu
    -0.88
     technik
    -0.88
     finition
    -0.88
     diminta
    -0.87
    два
    -0.87
    hala
    -0.87
    POSITIVE LOGITS
    en
    1.00
    ne
    0.98
    pa
    0.98
    p
    0.96
    na
    0.93
    ig
    0.91
     And
    0.90
    un
    0.90
    oulos
    0.89
    or
    0.88
    Activations Density 0.000%

    No Known Activations