© 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. 22-GEMMASCOPE-RES-131K
    7. 12630
    Prev
    Next
    INDEX
    Explanations

    numbered lists, code, or punctuation

    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_22/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
    <eos>
    -2.14
    Koordin
    -0.98
    =((
    -0.93
    OBJETIVOS
    -0.92
    チー
    -0.91
    romyalgia
    -0.90
    thard
    -0.90
    षण
    -0.89
     opět
    -0.87
    publisher
    -0.85
    POSITIVE LOGITS
    сыз
    0.91
    是最
    0.82
    R
    0.81
    N
    0.80
    P
    0.80
    顺便
    0.79
    疑问
    0.79
    etap
    0.78
    ();
    0.77
    rías
    0.77
    Activations Density 0.041%

    No Known Activations