© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69696
    Prev
    Next
    INDEX
    Explanations

    discussing children

    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
    逦
    -1.62
    as
    -1.48
    ge
    -1.45
    ok
    -1.44
    就能
    -1.43
    return
    -1.35
     risking
    -1.33
    挖掘
    -1.33
    if
    -1.32
    el
    -1.31
    POSITIVE LOGITS
    ')):
    1.55
    Џ
    1.45
     Actress
    1.38
    德國
    1.35
    uniqlo
    1.34
    האם
    1.30
    klar
    1.24
    Mbps
    1.23
    הת
    1.23
     място
    1.23
    Activations Density 0.018%

    No Known Activations