© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26690
    Prev
    Next
    INDEX
    Explanations

    birth of a child or family member

    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_22/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
    -
    -1.25
     or
    -1.22
     can
    -1.20
    l
    -1.16
     -
    -1.12
    当前
    -1.05
    ...
    -1.00
     Examples
    -0.99
     for
    -0.98
    b
    -0.98
    POSITIVE LOGITS
     colorear
    1.56
     colorir
    1.50
     ویتامین
    1.38
    첫
    1.37
    Spes
    1.31
    Kamera
    1.31
    чера
    1.30
     menambah
    1.29
     ativar
    1.29
    According
    1.28
    Activations Density 0.031%

    No Known Activations