© 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. 22-GEMMASCOPE-RES-131K
    7. 68140
    Prev
    Next
    INDEX
    Explanations

    opinions about food and meals

    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_22/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
    ApJ
    -1.46
     useful
    -1.34
     movement
    -1.22
     бампер
    -1.22
     protection
    -1.22
    取り付け
    -1.20
     security
    -1.19
     hardware
    -1.18
     this
    -1.17
     coffee
    -1.17
    POSITIVE LOGITS
     ویتامین
    1.84
    ׇ
    1.64
     cucchiai
    1.59
     cukru
    1.53
     municípios
    1.50
    prakti
    1.41
    Firstly
    1.38
    щення
    1.38
     abonnement
    1.37
     Rabatt
    1.36
    Activations Density 0.072%

    No Known Activations