© 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. 22-GEMMASCOPE-RES-131K
    7. 16670
    Prev
    Next
    INDEX
    Explanations

    Apache software license

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

    The neuron spikes on occurrences of “Apache” (and related license‐header tokens like ASF), effectively detecting Apache license boilerplate.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .”
    -2.86
    。
    -2.45
    様の
    -2.05
    の基本
    -2.02
    のおすすめ
    -2.00
     regiões
    -1.98
    ならではの
    -1.96
    様が
    -1.93
    の人気
    -1.91
    に座
    -1.91
    POSITIVE LOGITS
    谆
    2.02
     宝宝
    1.98
    +}\
    1.94
    *}$
    1.89
    </td>
    1.85
    ка
    1.84
    *}\
    1.84
    tidumbre
    1.83
    ⢧
    1.80
    ࿙
    1.78
    Activations Density 0.057%

    No Known Activations