© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31907
    Prev
    Next
    INDEX
    Explanations

    javascript code and academic terms

    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
    providedIn
    -1.00
    faatkan
    -0.95
    ずる
    -0.89
     aventures
    -0.87
    ικοί
    -0.86
    zember
    -0.85
    [])
    -0.85
    Marriage
    -0.84
    Choosing
    -0.84
     skut
    -0.84
    POSITIVE LOGITS
    this
    1.05
    super
    1.03
     super
    1.02
    这位
    0.96
     شام
    0.84
    granate
    0.83
     plus
    0.81
     этой
    0.79
     this
    0.77
     unfinished
    0.75
    Activations Density 0.002%

    No Known Activations