© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103322
    Prev
    Next
    INDEX
    Explanations

    alternate [x]

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on occurrences of the word “alternate” (and its variants like “alternative” or the abbreviation “alt”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    the
    -3.77
    ’
    -3.09
    }$
    -2.47
    둔
    -2.44
    see
    -2.36
    鶫
    -2.36
     \
    -2.31
    诬
    -2.25
    io
    -2.19
    ak
    -2.17
    POSITIVE LOGITS
    ↵
    3.86
     supremely
    2.59
     weirdly
    2.53
    其妙
    2.53
     poignant
    2.52
     unrelenting
    2.44
     exquisitely
    2.42
     exuberant
    2.41
    
    2.33
    넋
    2.30
    Activations Density 0.002%

    No Known Activations