© 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. 130269
    Prev
    Next
    INDEX
    Explanations

    The neuron flags imperative statements that mutate state—assignments or method/function calls that produce side effects.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    rounding mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    including
    -0.94
    ที่
    -0.91
    plit
    -0.90
    сками
    -0.87
    bakken
    -0.85
    assium
    -0.84
    Imports
    -0.84
    Including
    -0.84
    🏡
    -0.83
     português
    -0.83
    POSITIVE LOGITS
    ҟ
    0.97
     われ
    0.93
     nosso
    0.91
     didn
    0.91
    ดย
    0.89
     naše
    0.89
     vuelto
    0.88
     our
    0.88
     began
    0.88
    ayaquil
    0.85
    Activations Density 0.011%

    No Known Activations