© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84165
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
    {
    -2.69
    ]
    -2.67
     be
    -2.67
     dengan
    -2.42
    t
    -2.22
    ⃙
    -2.17
    光芒
    -2.13
     voor
    -2.11
    k
    -2.11
    嵛
    -2.09
    POSITIVE LOGITS
    ↵↵
    2.92
    
    2.53
     invokes
    2.41
     sorgfäl
    2.39
     portrayal
    2.36
     individuellen
    2.22
     stirs
    2.22
     arguments
    2.20
    淠
    2.19
    
    2.17
    Activations Density 0.003%

    No Known Activations