© 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. 69902
    Prev
    Next
    INDEX
    Explanations

    constitute precedent or fraud

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

    The neuron detects the intensifier phrase “bordering on” (and similar “akin to” constructions) in text.

    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
     habang
    -1.34
    destructive
    -1.32
     journeys
    -1.30
    uma
    -1.30
     with
    -1.28
     his
    -1.27
    νης
    -1.25
     instagram
    -1.25
    THERE
    -1.25
     känna
    -1.23
    POSITIVE LOGITS
     a
    2.17
    ╽
    1.53
    要求
    1.53
    وفق
    1.45
     même
    1.41
    ֟
    1.41
    estaba
    1.41
     вони
    1.41
     estos
    1.40
    ثل
    1.39
    Activations Density 0.038%

    No Known Activations