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. 8557
    Prev
    Next
    INDEX
    Explanations

    location services privacy data

    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
     bébé
    -0.91
    ânico
    -0.89
     lokasi
    -0.84
    🙌
    -0.81
    地點
    -0.81
    ères
    -0.81
     Años
    -0.81
     yere
    -0.80
     pikir
    -0.80
    Đặc
    -0.79
    POSITIVE LOGITS
     Services
    0.94
     services
    0.90
    substring
    0.83
     actualización
    0.82
     Deg
    0.81
     breakaway
    0.76
     quotient
    0.75
     acidosis
    0.73
    addressed
    0.73
     withal
    0.73
    Activations Density 0.015%

    No Known Activations