© 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. 10-GEMMASCOPE-RES-131K
    4. 9586
    Prev
    Next
    INDEX
    Explanations

    Hallelujah and names like Moffat, Andres

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

    The neuron fires on unusually rare or uncommon tokens (i.e. infrequent words or names) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -2.95
    敺
    -2.56
    และ
    -2.48
    hasilkan
    -2.42
     iſt
    -2.36
    𞤵
    -2.33
     málaga
    -2.30
    盦
    -2.30
    蟜
    -2.30
    觧
    -2.27
    POSITIVE LOGITS
     While
    3.45
     If
    2.59
     Of
    2.42
    讴
    2.25
     мы
    2.20
    荟
    2.16
     tidak
    2.14
     Not
    2.14
     Although
    2.11
    jenigen
    2.11
    Activations Density 0.016%

    No Known Activations