© 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. 34-GEMMASCOPE-RES-131K
    7. 54030
    Prev
    Next
    INDEX
    Explanations

    serialization attributes

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

    The neuron fires on occurrences of enum types and their members (e.g. “GenerationType.AUTO,” “AccessLevel,” “MemberSerialization.OptIn,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     received
    -1.09
     knows
    -0.88
     contributed
    -0.84
     ultimately
    -0.82
     from
    -0.81
     probably
    -0.79
     móng
    -0.79
     listened
    -0.78
     Geräten
    -0.77
     will
    -0.77
    POSITIVE LOGITS
     chanteur
    1.05
    lichten
    0.99
    
    0.91
     Strategie
    0.88
     INCLUDE
    0.85
     INSERT
    0.85
    COME
    0.84
     dési
    0.84
     porad
    0.84
    Policy
    0.83
    Activations Density 0.013%

    No Known Activations