© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4354
    Prev
    Next
    INDEX
    Explanations

    she/sh/mish and related words

    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
    đèn
    -0.81
     aumentado
    -0.81
    redmi
    -0.76
    それにしても
    -0.74
    hộp
    -0.74
    ائق
    -0.73
    ⤴
    -0.73
     gráficos
    -0.72
    SEPARATOR
    -0.72
    GetList
    -0.69
    POSITIVE LOGITS
    绝
    0.86
    Hochspringen
    0.84
    ={({
    0.79
    unteering
    0.78
     broken
    0.78
    老师
    0.76
    ようです
    0.75
    Routine
    0.75
    Je
    0.74
    BMC
    0.73
    Activations Density 0.007%

    No Known Activations