© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103805
    Prev
    Next
    INDEX
    Explanations

    classification and technical 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
    Another
    -0.85
     now
    -0.75
    :\/\/
    -0.74
     would
    -0.72
     why
    -0.72
     MMA
    -0.71
    AddComponent
    -0.71
     окру
    -0.71
    Why
    -0.70
     Another
    -0.70
    POSITIVE LOGITS
     subclass
    0.99
    Subclass
    0.90
    륭
    0.87
    CPC
    0.84
    興奮
    0.84
     IPC
    0.79
     COST
    0.79
     trumps
    0.78
    ŚĆ
    0.77
    appropriate
    0.77
    Activations Density 0.105%

    No Known Activations