© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58384
    Prev
    Next
    INDEX
    Explanations

    p-values and significance levels

    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
     Ignoring
    -0.85
     chỉ
    -0.83
     ليس
    -0.77
    Nhi
    -0.75
    ਿੰ
    -0.74
    SqlClient
    -0.73
    μά
    -0.72
    该
    -0.70
    volved
    -0.70
    原神
    -0.70
    POSITIVE LOGITS
     alpha
    1.05
     α
    1.05
     Alpha
    0.93
     considered
    0.86
    alpha
    0.86
    AuthGuard
    0.85
    ALPHA
    0.84
     alfa
    0.82
     p
    0.81
     ≤
    0.81
    Activations Density 0.016%

    No Known Activations