© 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. 22-GEMMASCOPE-RES-131K
    7. 98629
    Prev
    Next
    INDEX
    Explanations

    city and state

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

    The neuron strongly activates on three-digit numerals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    '
    -1.37
    “
    -1.28
    ,
    -1.19
    ’
    -1.13
     штук
    -1.11
    WITH
    -1.09
     způso
    -1.06
     =='
    -1.06
     グッズ
    -1.05
    ＝
    -1.05
    POSITIVE LOGITS
     stolet
    1.24
    īdz
    1.13
     gustó
    1.12
    팻
    1.09
     hollows
    1.09
    三重
    1.07
     nalazi
    1.07
     where
    1.07
     häufig
    1.06
     dilaporkan
    1.02
    Activations Density 0.095%

    No Known Activations