© 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. 1202
    Prev
    Next
    INDEX
    Explanations

    price tag bill label packets

    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
    蟶
    -1.84
     lolita
    -1.68
     Öz
    -1.68
     avengers
    -1.67
     luffy
    -1.66
     哪些
    -1.66
    </h5>
    -1.64
     uchiha
    -1.63
     lmfao
    -1.58
     hater
    -1.58
    POSITIVE LOGITS
    iſter
    1.92
    事も
    1.91
     delicado
    1.84
     profundos
    1.77
     проектов
    1.76
     inversores
    1.74
    優しく
    1.73
     compradores
    1.73
     científico
    1.72
    感のある
    1.72
    Activations Density 0.005%

    No Known Activations