© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81046
    Prev
    Next
    INDEX
    Explanations

    counting one or quantities

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

    The neuron is picking out unusually rare or low-frequency tokens.

    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
     pleaf
    -1.26
    prnewswire
    -1.20
     無地
    -1.19
     poffe
    -1.17
     your
    -1.15
    StackNavigator
    -1.14
    一堆
    -1.13
     gradova
    -1.11
     seuls
    -1.11
    \#:
    -1.09
    POSITIVE LOGITS
     one
    9.19
    One
    3.75
     одного
    3.69
    หนึ่ง
    3.56
     одной
    3.42
     یکی
    3.42
    one
    3.23
     ones
    3.22
     один
    3.20
     одним
    3.16
    Activations Density 0.292%

    No Known Activations