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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48313
    Prev
    Next
    INDEX
    Explanations

    weight loss and gain

    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
     are
    -1.99
    '
    -1.91
     VARIOUS
    -1.89
     catégories
    -1.78
     oferece
    -1.77
     rams
    -1.74
    スム
    -1.73
    プレミアム
    -1.72
    ).
    -1.71
    绷
    -1.71
    POSITIVE LOGITS
     její
    1.91
    蠵
    1.84
    媗
    1.82
    ₶
    1.78
    ஂ
    1.77
     که
    1.73
     joyería
    1.71
     männ
    1.71
    ”？
    1.71
     coloridos
    1.67
    Activations Density 0.005%

    No Known Activations