© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103422
    Prev
    Next
    INDEX
    Explanations

    either / neither

    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
     Whatever
    -1.10
    Any
    -1.09
     any
    -1.09
    either
    -1.01
     Either
    -1.01
    Whatever
    -1.00
    anything
    -0.98
     one
    -0.97
    whatever
    -0.97
    Even
    -0.95
    POSITIVE LOGITS
     neither
    1.43
     tampoco
    1.02
     heller
    1.02
    ύτε
    0.96
    Neither
    0.93
    neither
    0.84
    也没
    0.82
    白い
    0.82
     ea
    0.81
    居る
    0.80
    Activations Density 0.060%

    No Known Activations