© 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. 10-GEMMASCOPE-RES-131K
    4. 104338
    Prev
    Next
    INDEX
    Explanations

    description of related art

    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_10/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
    étit
    -1.45
     burgeoning
    -1.45
     for
    -1.43
    ;
    -1.42
    ?
    -1.40
    orteur
    -1.37
     exuberant
    -1.36
    dasarkan
    -1.33
    ”،
    -1.32
     exploring
    -1.30
    POSITIVE LOGITS
     verhind
    1.70
     {
    
    
    1.47
    </h1>
    1.47
    </h3>
    1.45
     remarkably
    1.38
     vastly
    1.35
     abſ
    1.34
    lllllll
    1.33
    úst
    1.31
     asseg
    1.27
    Activations Density 0.053%

    No Known Activations