© 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. 1062
    Prev
    Next
    INDEX
    Explanations

    title of organization

    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
    튿
    -1.85
    賸
    -1.80
    呿
    -1.80
    聼
    -1.76
    seems
    -1.76
    ꪳ
    -1.74
    繙
    -1.72
    aning
    -1.69
    lllll
    -1.63
     CERTAIN
    -1.63
    POSITIVE LOGITS
     of
    2.53
    >
    1.65
     to
    1.54
     mismo
    1.49
     same
    1.49
     bernama
    1.46
     podemos
    1.45
    ⅖
    1.42
     bele
    1.39
     設備
    1.35
    Activations Density 0.022%

    No Known Activations