© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128086
    Prev
    Next
    INDEX
    Explanations

    Ann Arbor, arbor.js, AppHarbor

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

    The neuron activates whenever the substring “Arbor” appears (e.g. in “Ann Arbor”).

    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
     patrulla
    -2.84
    擽
    -2.67
     verrez
    -2.47
     laatste
    -2.33
    퐿
    -2.31
     estadía
    -2.30
     recevrez
    -2.28
     caduta
    -2.27
    𝄆
    -2.27
    慊
    -2.25
    POSITIVE LOGITS
    ing
    2.58
    Y
    2.55
    .;
    2.42
    .,
    2.23
    ."
    2.19
    I
    2.16
     arbor
    2.16
    ,.
    2.06
     enriching
    2.06
     哪些
    2.05
    Activations Density 0.004%

    No Known Activations