© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75151
    Prev
    Next
    INDEX
    Explanations

    criminal activities

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

    The neuron fires on numerical and quantitative expressions (e.g. counts, measurements, dates).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     necessary
    -1.02
     how
    -1.01
     its
    -0.99
     visibilidad
    -0.96
     vermogen
    -0.93
     when
    -0.91
     CATH
    -0.90
     required
    -0.90
     capacity
    -0.90
     impuestos
    -0.89
    POSITIVE LOGITS
     similar
    1.16
     모두
    1.15
    Similar
    1.12
    sterious
    1.06
    setdefault
    1.05
    どうやら
    1.03
     misterioso
    1.02
     mysterious
    0.99
     заболевания
    0.99
    这几
    0.99
    Activations Density 0.074%

    No Known Activations