© 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. 10-GEMMASCOPE-RES-131K
    7. 105481
    Prev
    Next
    INDEX
    Explanations

    Idaho

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

    The neuron consistently activates on the token “Idaho,” flagging every occurrence of that specific place name.

    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
     男孩
    -2.44
    驒
    -2.39
    َم
    -2.23
    럴
    -2.22
     hermosas
    -2.17
    ︲
    -2.16
    很棒
    -2.14
    骘
    -2.13
     сказал
    -2.11
    鯷
    -2.09
    POSITIVE LOGITS
     In
    2.47
    翾
    2.14
     \
    2.13
     batas
    2.05
    ,“
    2.02
     signifies
    1.98
    但在
    1.89
    =“
    1.88
    fishes
    1.84
    wurst
    1.81
    Activations Density 0.002%

    No Known Activations