© 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. 107673
    Prev
    Next
    INDEX
    Explanations

    version numbers and 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
    contenido
    -0.65
    怪
    -0.62
    𝜃
    -0.61
    fro
    -0.60
     Desa
    -0.59
     Duckworth
    -0.59
     Sealing
    -0.59
    アの
    -0.58
    woods
    -0.57
     vezet
    -0.57
    POSITIVE LOGITS
    FlatList
    0.75
    匿名使用者
    0.75
    OPSIS
    0.73
     Lucia
    0.72
    upta
    0.71
    תיים
    0.71
     анти
    0.71
    ligible
    0.70
    bbons
    0.69
    avascript
    0.68
    Activations Density 0.046%

    No Known Activations