© 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. 11800
    Prev
    Next
    INDEX
    Explanations

    implied warranty or http

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

    The neuron fires primarily on numeric tokens—things like version numbers, reference indices, permissions codes, and other digit sequences.

    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
     prøve
    -0.85
     ugu
    -0.81
    otheby
    -0.79
     TestCase
    -0.79
     ;-;
    -0.79
     🥲
    -0.78
    ضم
    -0.77
    🥺
    -0.77
     >:
    -0.76
     endothelial
    -0.75
    POSITIVE LOGITS
    承诺
    0.81
    Renee
    0.75
     vied
    0.75
    뤼
    0.75
     ruffled
    0.73
    partly
    0.73
     puder
    0.72
     الحر
    0.71
    わけです
    0.71
    ряду
    0.70
    Activations Density 0.000%

    No Known Activations