© 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. 36037
    Prev
    Next
    INDEX
    Explanations

    court characters and social settings

    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
     vinos
    -1.67
     vanil
    -1.53
    ૉ
    -1.52
     HomeComponent
    -1.40
    шому
    -1.40
     précé
    -1.40
     LoginComponent
    -1.34
    𝛼
    -1.31
     basili
    -1.30
     Ә
    -1.30
    POSITIVE LOGITS
     by
    1.51
    mathfrak
    1.34
    ÈNE
    1.30
    暧
    1.27
     masculine
    1.26
     miei
    1.25
    คุณ
    1.24
    Ꮖ
    1.23
    достатки
    1.20
    nī
    1.19
    Activations Density 0.020%

    No Known Activations