© 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. 60386
    Prev
    Next
    INDEX
    Explanations

    For [people/pronouns]

    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
     for
    -1.54
     you
    -1.44
     many
    -1.28
     everyone
    -1.27
     You
    -1.16
     while
    -1.12
    We
    -1.11
     people
    -1.10
     others
    -1.10
     several
    -1.08
    POSITIVE LOGITS
     it
    3.02
     this
    1.98
     there
    1.75
     это
    1.67
    来说
    1.63
    而言
    1.44
    來說
    1.30
     этого
    1.23
     who
    1.17
     این
    1.17
    Activations Density 0.040%

    No Known Activations