© 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. 34-GEMMASCOPE-RES-131K
    7. 117603
    Prev
    Next
    INDEX
    Explanations

    justices and justifications

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

    The neuron consistently fires on the character sequence “Jus” (i.e. tokens beginning with “Jus,” such as “Jus,” “Justicia,” “Justus,” or “Justify”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     just
    -1.00
     vừa
    -0.90
     Unternehmens
    -0.76
    SKIN
    -0.74
    поль
    -0.71
    nity
    -0.71
    lijkheid
    -0.71
    ктория
    -0.70
    ностей
    -0.70
    <th>
    -0.70
    POSITIVE LOGITS
    觊
    0.82
    aume
    0.79
    Française
    0.77
    ᱼ
    0.77
     Leagues
    0.74
    訣
    0.73
     जग
    0.71
     overlapped
    0.71
     mingled
    0.71
     drenched
    0.71
    Activations Density 0.012%

    No Known Activations