© 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. 22-GEMMASCOPE-RES-131K
    7. 128605
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on the “->” arrow symbol used to denote directed connections or transitions (e.g. edges in routes, circuit flows, activity stacks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    then

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    must
    -1.11
    ha
    -1.11
    d
    -1.10
    har
    -1.06
     torsdag
    -1.03
    ir
    -1.01
    las
    -1.01
    ng
    -1.01
    uh
    -1.01
     &
    -1.00
    POSITIVE LOGITS
     then
    1.41
     یکی
    1.03
    然后
    1.03
    cnbc
    1.02
     kvalit
    1.02
     プラン
    0.99
    uniqlo
    0.98
    然後
    0.96
     потім
    0.96
     accepté
    0.96
    Activations Density 0.038%

    No Known Activations