© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15823
    Prev
    Next
    INDEX
    Explanations

    back and forth

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

    The neuron fires on instances of the phrase “back and forth,” particularly on the word “forth” (and its surrounding context) indicating repeated motion or alternation.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    {
    -2.20
    </b>
    -1.98
     and
    -1.80
    诟
    -1.76
     –
    -1.67
     теми
    -1.66
    あなたが
    -1.63
    这让
    -1.59
    に行って
    -1.56
     آمریک
    -1.55
    POSITIVE LOGITS
     between
    2.06
    
    1.91
    z
    1.86
    x
    1.80
     置物
    1.73
     ausger
    1.73
    月中旬
    1.70
    龉
    1.70
    妡
    1.69
     Frühjahr
    1.68
    Activations Density 0.004%

    No Known Activations