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. 7927
    Prev
    Next
    INDEX
    Explanations

    international hotel management

    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
     facility
    -0.84
     management
    -0.81
    ₲
    -0.71
    Capacity
    -0.70
     capacity
    -0.69
     tickets
    -0.67
     тик
    -0.67
    推特
    -0.67
    Pati
    -0.66
     consequent
    -0.66
    POSITIVE LOGITS
     Arne
    0.89
     einges
    0.88
     PIP
    0.84
    PIP
    0.81
     distribuzione
    0.81
    ridis
    0.78
     هتل
    0.77
    不知
    0.77
    llte
    0.76
     distribución
    0.76
    Activations Density 0.011%

    No Known Activations