Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 159
    Prev
    Next
    INDEX
    Explanations

    android components and code structure

    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
     nutricional
    -0.83
     Cardio
    -0.75
     اللح
    -0.75
     hardships
    -0.73
     Conditioner
    -0.73
    spice
    -0.72
    OLY
    -0.72
    oom
    -0.72
    wheel
    -0.72
    𝙐
    -0.72
    POSITIVE LOGITS
    mj
    1.05
     MJ
    0.93
     mj
    0.83
    MJ
    0.81
     pulling
    0.79
    Oso
    0.71
    aerop
    0.70
     Begin
    0.68
     discharging
    0.67
    actress
    0.67
    Activations Density 0.002%

    No Known Activations