© 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. 110753
    Prev
    Next
    INDEX
    Explanations

    Category and URL metadata

    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
    forRoot
    -0.98
     Untuk
    -0.93
    thető
    -0.81
    王一
    -0.80
    handlung
    -0.79
     Pha
    -0.78
    Pha
    -0.77
    jsko
    -0.77
    ModelForm
    -0.75
    💺
    -0.73
    POSITIVE LOGITS
     common
    0.90
     again
    0.85
     shared
    0.80
    共通
    0.77
     paznok
    0.73
    meida
    0.72
     routed
    0.71
    common
    0.70
    级的
    0.70
     Common
    0.69
    Activations Density 0.006%

    No Known Activations