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. 110062
    Prev
    Next
    INDEX
    Explanations

    NBA 2K playbook

    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
     índice
    -0.85
    Twe
    -0.79
     Firebase
    -0.78
    voor
    -0.78
     Phạm
    -0.76
     intress
    -0.75
     sonriente
    -0.74
     perquè
    -0.73
    редиенты
    -0.71
     nü
    -0.71
    POSITIVE LOGITS
    licant
    0.89
    ulli
    0.86
    CERN
    0.79
    Balance
    0.78
    ursor
    0.76
     napis
    0.75
    ppus
    0.75
    IENCE
    0.75
    asjoner
    0.74
     smut
    0.74
    Activations Density 0.010%

    No Known Activations