© 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. 69483
    Prev
    Next
    INDEX
    Explanations

    Windows UI development and fragments

    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
    parseDouble
    -1.75
    ABASES
    -1.53
     beide
    -1.52
    力
    -1.52
    </h4>
    -1.52
    MBOL
    -1.51
     câmera
    -1.49
     defies
    -1.49
    GIVEREF
    -1.49
    izó
    -1.45
    POSITIVE LOGITS
    4
    2.17
    1
    2.06
    6
    1.82
     this
    1.79
     such
    1.67
    7
    1.67
    3
    1.66
    9
    1.65
    8
    1.52
    ちょうど
    1.47
    Activations Density 0.029%

    No Known Activations