© 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. 76310
    Prev
    Next
    INDEX
    Explanations

    excellent quality and positive descriptions

    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
     alcune
    -1.43
    
    -1.40
    ⎔
    -1.36
     to
    -1.36
    🛇
    -1.35
    驺
    -1.34
    犼
    -1.33
    骘
    -1.30
    戆
    -1.30
    伥
    -1.30
    POSITIVE LOGITS
     quality
    1.48
    ly
    1.42
    Â
    1.41
     qualities
    1.41
    _
    1.38
    !
    1.38
     choice
    1.34
    "
    1.32
    ↵
    1.29
    <strong>
    1.27
    Activations Density 0.017%

    No Known Activations