© 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. 116739
    Prev
    Next
    INDEX
    Explanations

    configuration and code prefixes

    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
     idiot
    -0.79
    iense
    -0.69
    plasia
    -0.69
    姹
    -0.68
    Mixin
    -0.68
     integrals
    -0.67
     potenza
    -0.67
    
    -0.67
    詡
    -0.67
     accidents
    -0.66
    POSITIVE LOGITS
     property
    0.91
     команди
    0.84
     queue
    0.84
     Bianco
    0.79
     PROPERTY
    0.77
     parallelism
    0.75
    <0xF0>
    0.72
    marginTop
    0.70
     uniqu
    0.69
     Networking
    0.69
    Activations Density 0.018%

    No Known Activations