© 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. 22-GEMMASCOPE-RES-131K
    7. 39178
    Prev
    Next
    INDEX
    Explanations

    y variable in plotting

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

    The neuron fires on numeric literals (e.g. numbers like 4, 99, 564, 142, etc.) in code—i.e. it detects numeric constants.

    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
     rubrique
    -1.00
    }^{*}$
    -0.99
    ments
    -0.96
    ariConfig
    -0.95
    FontAwesomeIcon
    -0.94
    arusian
    -0.94
    blende
    -0.94
    cule
    -0.92
    rceil
    -0.92
    etal
    -0.91
    POSITIVE LOGITS
     their
    1.22
     πρ
    1.00
    얹
    0.90
     interesar
    0.90
    cadeau
    0.88
     всегда
    0.87
    inverno
    0.85
    écrire
    0.84
    zookeeper
    0.82
    CIÓN
    0.81
    Activations Density 0.004%

    No Known Activations