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. 34-GEMMASCOPE-RES-131K
    4. 110041
    Prev
    Next
    INDEX
    Explanations

    Valentine and related holidays

    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
    pdp
    -0.91
     LoginComponent
    -0.91
     well
    -0.80
    solved
    -0.78
    人都
    -0.77
    joner
    -0.77
    SOLVED
    -0.75
    身長
    -0.75
    nyata
    -0.74
     April
    -0.73
    POSITIVE LOGITS
    たつ
    0.89
     candy
    0.88
     rurale
    0.85
     rade
    0.83
     bebê
    0.82
    chic
    0.80
    issipp
    0.80
    lowers
    0.78
    kills
    0.78
    结语
    0.78
    Activations Density 0.010%

    No Known Activations