© 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. 79530
    Prev
    Next
    INDEX
    Explanations

    like phrases

    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
    CHAIN
    -0.96
     skulls
    -0.90
     المختلف
    -0.89
    SELF
    -0.88
    に
    -0.87
    тные
    -0.87
    让
    -0.85
    alipay
    -0.84
     المعرف
    -0.84
     popoli
    -0.84
    POSITIVE LOGITS
     other
    0.98
    thenes
    0.91
     any
    0.88
    Gesam
    0.88
    いかがでしたか
    0.87
     öl
    0.84
    的意思
    0.83
    ntomas
    0.82
    DEPORTES
    0.82
     pincel
    0.82
    Activations Density 0.048%

    No Known Activations