© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99352
    Prev
    Next
    INDEX
    Explanations

    justification and justified contexts

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

    The neuron activates on occurrences of the word “justification” (and its close morphological variants).

    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
    -3.19
     This
    -2.86
    llavero
    -2.77
    〮
    -2.59
    butuhkan
    -2.59
     Anſ
    -2.59
     ``
    -2.53
     You
    -2.52
    了起来
    -2.44
    इटम
    -2.41
    POSITIVE LOGITS
    旁邊
    3.02
     الثالث
    2.64
    在他的
    2.59
    '
    2.55
    逦
    2.50
     塗装
    2.48
     remainder
    2.39
    But
    2.39
    媳妇
    2.39
    <bos>
    2.38
    Activations Density 0.003%

    No Known Activations