© 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. 3832
    Prev
    Next
    INDEX
    Explanations

    development of technologies

    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
     involucrados
    -1.73
    Ṇ
    -1.58
    eſ
    -1.52
     Chriſt
    -1.52
     Saltar
    -1.48
    </h1>
    -1.48
    久し
    -1.48
    カシ
    -1.48
    取决
    -1.46
    婊
    -1.46
    POSITIVE LOGITS
     $
    2.22
    6
    1.82
    7
    1.64
    an
    1.58
    st
    1.55
    4
    1.55
    </em>
    1.52
    b
    1.52
    0
    1.44
    ]
    1.43
    Activations Density 0.010%

    No Known Activations