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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99094
    Prev
    Next
    INDEX
    Explanations

    one or, when relevant

    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_34/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
    進入
    -0.88
     Utiliza
    -0.85
     dinoss
    -0.84
     cenu
    -0.83
    CHARS
    -0.82
     tarifas
    -0.82
    来店
    -0.81
    &=\
    -0.80
    ,$_
    -0.79
    なった
    -0.79
    POSITIVE LOGITS
    èdia
    0.88
    olucion
    0.88
     Promise
    0.79
     cross
    0.78
    нгредієнти
    0.77
    分别是
    0.77
     подготовка
    0.76
    这几
    0.76
     seleccionados
    0.76
    Afin
    0.75
    Activations Density 0.001%

    No Known Activations