© 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. 36048
    Prev
    Next
    INDEX
    Explanations

    version.endswith(('a', 'b', 'rc'))

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

    The neuron reliably fires on numeric literals (including integers and decimals) and comparison operators involving them.

    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
     trecut
    -0.82
     NBA
    -0.81
    Apesar
    -0.80
    otra
    -0.78
    телен
    -0.76
    рода
    -0.76
    NBA
    -0.75
     blandt
    -0.75
    ATTR
    -0.74
     ApJ
    -0.74
    POSITIVE LOGITS
    زع
    0.90
     too
    0.88
    undes
    0.84
     ofreciendo
    0.82
     recordar
    0.78
    colades
    0.77
    chante
    0.77
    üler
    0.76
    ล่า
    0.75
    忘了
    0.74
    Activations Density 0.011%

    No Known Activations