© 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. 34-GEMMASCOPE-RES-131K
    4. 59921
    Prev
    Next
    INDEX
    Explanations

    level up and upgrade

    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
     GameObject
    -0.76
    ญ
    -0.74
    ERA
    -0.72
     nerfs
    -0.71
    artiges
    -0.69
    decre
    -0.68
    Toolbar
    -0.68
     Regeneration
    -0.68
     abstain
    -0.67
     pí
    -0.67
    POSITIVE LOGITS
     level
    1.42
     levels
    1.36
     upgrade
    1.34
     maxed
    1.23
     lvl
    1.22
    升
    1.21
     upgrading
    1.20
    Level
    1.19
    level
    1.18
    Lvl
    1.17
    Activations Density 0.005%

    No Known Activations