© 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. 84424
    Prev
    Next
    INDEX
    Explanations

    copyright reserved outcomes effects include

    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
    getExternal
    -0.71
     heads
    -0.67
    IDEO
    -0.65
    Ide
    -0.65
    ია
    -0.65
     انتخاب
    -0.64
    哚
    -0.64
    ideo
    -0.64
     sight
    -0.63
    moor
    -0.63
    POSITIVE LOGITS
    usitis
    0.77
    EMPL
    0.76
    RowCount
    0.69
    TypedDataSet
    0.67
     Judaism
    0.66
     contenidos
    0.66
     rod
    0.66
     ایک
    0.66
    мас
    0.65
     Wend
    0.65
    Activations Density 0.076%

    No Known Activations