© 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. 119217
    Prev
    Next
    INDEX
    Explanations

    we can/could/should

    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
     my
    -1.55
     herself
    -1.42
     itself
    -1.41
     himself
    -1.35
     μου
    -1.23
    ﮩ
    -1.20
     themselves
    -1.20
    worden
    -1.18
    自分は
    -1.18
    inio
    -1.11
    POSITIVE LOGITS
     ourselves
    4.31
     our
    3.19
     we
    3.00
    We
    2.34
    Our
    2.27
     We
    2.25
    我们
    1.98
     داریم
    1.98
    我們
    1.95
     我们
    1.95
    Activations Density 0.064%

    No Known Activations