© 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. 22-GEMMASCOPE-RES-131K
    7. 68354
    Prev
    Next
    INDEX
    Explanations

    by the law

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

    The neuron detects formal requirement clauses, especially the word “by” (as in “required by the …”) in legal or license‐style text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    uristic
    -1.04
    可以看到
    -1.03
    hability
    -0.96
     puteți
    -0.93
    eload
    -0.92
     perce
    -0.91
    bner
    -0.90
    Примеча
    -0.88
    bió
    -0.88
    資料來源
    -0.86
    POSITIVE LOGITS
     nature
    1.26
     circumstances
    1.24
     their
    1.17
     our
    1.03
     by
    1.03
     the
    1.03
     demanded
    0.99
     history
    0.98
     laws
    0.97
     demanding
    0.97
    Activations Density 0.060%

    No Known Activations