© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112224
    Prev
    Next
    INDEX
    Explanations

    court of criminal appeals

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

    The neuron fires on decimal-style numeric tokens (floating-point numbers).

    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
     by
    -2.14
     that
    -2.13
     which
    -2.09
     of
    -2.08
     through
    -2.03
     their
    -2.02
     for
    -1.95
    なんですね
    -1.78
     from
    -1.77
     tahun
    -1.74
    POSITIVE LOGITS
     lavable
    2.05
     jezt
    2.02
     murale
    1.74
     individuel
    1.67
     indeb
    1.67
     milj
    1.66
     herbes
    1.66
     klassi
    1.66
     durs
    1.66
     sektor
    1.64
    Activations Density 0.001%

    No Known Activations