© 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. 104277
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     também
    -1.38
     También
    -1.32
     auch
    -1.23
     hanya
    -1.23
     Also
    -1.19
     también
    -1.18
    РЫ
    -1.18
    づけ
    -1.16
    に行く
    -1.15
    lidene
    -1.13
    POSITIVE LOGITS
    個月
    1.27
    <bos>
    1.26
     herido
    1.25
     tuviera
    1.25
     hiciera
    1.20
    蕯
    1.18
    ‌.
    1.17
    項目
    1.14
    ┛
    1.11
    ஂ
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.