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. 110066
    Prev
    Next
    INDEX
    Explanations

    mathematical variable x

    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
    positive
    -0.79
    lope
    -0.78
    aute
    -0.77
    haupt
    -0.75
    neaux
    -0.74
     界
    -0.73
    想起
    -0.72
    ROSS
    -0.72
    прави
    -0.71
     attackers
    -0.71
    POSITIVE LOGITS
     location
    1.17
     x
    1.07
    Locatie
    0.98
    x
    0.98
    Lieu
    0.94
     locations
    0.94
     Diarrhea
    0.93
     위치
    0.85
     center
    0.84
     posición
    0.82
    Activations Density 0.026%

    No Known Activations