© 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. 34-GEMMASCOPE-RES-131K
    7. 97966
    Prev
    Next
    INDEX
    Explanations

    numbers followed by `]` or `=>`

    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
    ＊＊＊＊
    -1.36
    久し
    -1.36
    来週
    -1.33
    もうすぐ
    -1.32
    先週
    -1.30
    明日は
    -1.28
    にあります
    -1.25
     filós
    -1.23
    昨日の
    -1.20
    今月
    -1.20
    POSITIVE LOGITS
     is
    1.61
    so
    1.27
    1.23
     H
    1.21
     N
    1.19
     A
    1.19
     U
    1.19
     It
    1.17
     S
    1.15
     G
    1.15
    Activations Density 0.020%

    No Known Activations