© 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. 116915
    Prev
    Next
    INDEX
    Explanations

    UI element classes and attributes

    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
    =?,
    -0.94
    IZONT
    -0.93
    leeve
    -0.90
     标题
    -0.87
    icamente
    -0.87
    schmidt
    -0.84
    crackers
    -0.82
    forks
    -0.82
    DataSnapshot
    -0.81
     Ancak
    -0.81
    POSITIVE LOGITS
    class
    1.19
    _
    1.18
    -
    1.16
    __
    1.08
    Style
    0.95
     heridos
    0.94
    Class
    0.94
     다른
    0.94
     nécess
    0.92
     autre
    0.90
    Activations Density 0.039%

    No Known Activations