© 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. 10-GEMMASCOPE-RES-131K
    7. 124128
    Prev
    Next
    INDEX
    Explanations

    from scratch, in detail, by writing

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

    The neuron strongly fires on occurrences of “scratch,” in particular the phrase “from scratch” indicating something built or created anew.

    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
    </i>
    -1.88
    {
    -1.79
     denoted
    -1.59
    -1.50
     meest
    -1.47
    上来
    -1.45
    )),
    -1.45
     probable
    -1.45
    を使用した
    -1.43
     “
    -1.42
    POSITIVE LOGITS
    ؛
    1.80
    8
    1.74
    ,"
    1.68
     ''
    1.65
    ''
    1.63
    ca
    1.61
    However
    1.57
    ---
    1.57
     jedoch
    1.55
    ""
    1.54
    Activations Density 0.103%

    No Known Activations