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. 7881
    Prev
    Next
    INDEX
    Explanations

    tournament, event, competition names

    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
    łosi
    -0.84
     serviços
    -0.78
    łog
    -0.77
    tholes
    -0.77
    embols
    -0.76
    viers
    -0.75
    导师
    -0.75
    APPING
    -0.73
    わかる
    -0.72
     Skinny
    -0.72
    POSITIVE LOGITS
     Activities
    0.80
    实的
    0.77
    ที่จะ
    0.75
    ĵo
    0.74
     comment
    0.73
    shmi
    0.72
     саду
    0.72
    VPS
    0.72
    рою
    0.71
    آوری
    0.71
    Activations Density 0.004%

    No Known Activations