© 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. 95822
    Prev
    Next
    INDEX
    Explanations

    package declarations

    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
     to
    -1.84
    がありますが
    -1.44
    ですが
    -1.36
    かで
    -1.33
    廊下
    -1.33
    があり
    -1.32
     by
    -1.31
    pullover
    -1.29
    慟
    -1.26
    逡
    -1.25
    POSITIVE LOGITS
    1.56
    .
    1.53
     jaunes
    1.41
     romero
    1.34
    ぼく
    1.30
    /
    1.30
     applau
    1.25
     marqués
    1.22
    に似
    1.22
     contenta
    1.19
    Activations Density 0.010%
    No Known Activations