© 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. 83775
    Prev
    Next
    INDEX
    Explanations

    between

    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
     другого
    -1.42
     combination
    -1.36
     others
    -1.30
     других
    -1.25
    </b>
    -1.23
    遑
    -1.23
     sowohl
    -1.22
     other
    -1.20
    ‌
    -1.18
     или
    -1.16
    POSITIVE LOGITS
     them
    2.33
     the
    1.84
     между
    1.65
     these
    1.37
     him
    1.33
     between
    1.29
     sexes
    1.28
     genders
    1.28
     myself
    1.21
    她和
    1.20
    Activations Density 0.079%

    No Known Activations