© 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. 10-GEMMASCOPE-RES-131K
    4. 59521
    Prev
    Next
    INDEX
    Explanations

    mentions of wife or husband

    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_10/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
    絎
    -1.42
    !)
    -1.41
    !,
    -1.35
     в
    -1.32
     $^{\
    -1.30
    !),
    -1.30
    䊳
    -1.30
    ...)
    -1.27
     $_{
    -1.26
    なども
    -1.26
    POSITIVE LOGITS
    ementara
    1.48
     länder
    1.38
     Lesen
    1.36
     of
    1.35
     ПРО
    1.32
    brakk
    1.30
    xrLabel
    1.30
     Sahne
    1.30
    tvguide
    1.30
    treas
    1.30
    Activations Density 0.003%

    No Known Activations