© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59258
    Prev
    Next
    INDEX
    Explanations

    legal arguments and claims

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

    The neuron fires on the formal procedural‐history language you see in judicial opinions—phrases that introduce and describe the nature of the suit (e.g. “This is a suit brought in…” or “The objection urged against the ordinance…”).

    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
     acidente
    -1.71
    erà
    -1.53
     productivo
    -1.46
    pantalon
    -1.41
     apoio
    -1.41
     pacote
    -1.39
     nascimento
    -1.38
     acesso
    -1.35
     freio
    -1.32
     bawat
    -1.30
    POSITIVE LOGITS
     but
    2.05
     or
    1.88
     as
    1.82
     in
    1.80
     it
    1.70
     by
    1.65
     and
    1.60
    ينات
    1.53
     on
    1.52
    It
    1.41
    Activations Density 0.158%

    No Known Activations