© 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. 10-GEMMASCOPE-RES-131K
    7. 127667
    Prev
    Next
    INDEX
    Explanations

    foreclosure cases and sales

    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
    o
    -2.30
    ar
    -1.98
    f
    -1.83
    v
    -1.74
    volved
    -1.68
    </h3>
    -1.63
    おはよう
    -1.61
    section
    -1.57
    两人的
    -1.55
    ion
    -1.53
    POSITIVE LOGITS
     misschien
    1.91
     waarschijnlijk
    1.89
    骝
    1.81
    ↵
    1.72
     probabilmente
    1.66
     verdaderos
    1.65
     oggi
    1.62
     inderdaad
    1.60
     foreclosure
    1.59
     malheureusement
    1.58
    Activations Density 0.005%

    No Known Activations