© 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. 1222
    Prev
    Next
    INDEX
    Explanations

    toast and roast foods

    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
    ised
    -2.53
     pero
    -2.34
     専用
    -2.31
     THIS
    -2.25
    姽
    -2.23
     жидко
    -2.22
     cyclone
    -2.17
    ⩴
    -2.17
    ?"
    -2.14
    ?’
    -2.14
    POSITIVE LOGITS
    sandalia
    2.52
    ,
    2.27
    abonnement
    2.25
    {
    2.23
    是这样
    2.14
    ające
    2.11
    
    2.11
    ated
    2.03
    ⃚
    2.02
    錵
    1.96
    Activations Density 0.007%

    No Known Activations