© 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. 101897
    Prev
    Next
    INDEX
    Explanations

    court citations and names

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

    The neuron fires on the numeric line‐range indicators in unified diffs (the “–start,count” and “+start,count” hunk headers).

    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
     also
    -1.67
     a
    -1.59
     as
    -1.58
     to
    -1.49
     only
    -1.35
     three
    -1.34
     Allgemeinen
    -1.34
    ための
    -1.32
     instead
    -1.32
    틈
    -1.30
    POSITIVE LOGITS
    konstruktion
    1.25
    ghter
    1.25
     konkur
    1.19
     beiden
    1.16
     waarom
    1.16
     JUSTICE
    1.15
    lorin
    1.15
    婳
    1.14
    tanleria
    1.14
    writeField
    1.13
    Activations Density 0.059%

    No Known Activations