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. 8650
    Prev
    Next
    INDEX
    Explanations

    annual defense strategy

    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
     fé
    -0.77
     gial
    -0.73
     DM
    -0.72
     PR
    -0.72
     measured
    -0.71
     Sherry
    -0.71
     Telefon
    -0.69
    цева
    -0.68
     VIP
    -0.68
     wyd
    -0.67
    POSITIVE LOGITS
     ANNUAL
    0.94
    annual
    0.87
     annual
    0.85
     Armed
    0.84
     defense
    0.84
     TRX
    0.83
    armed
    0.83
     armed
    0.79
    Armed
    0.77
     NDA
    0.75
    Activations Density 0.043%

    No Known Activations