© 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. 34-GEMMASCOPE-RES-131K
    7. 60901
    Prev
    Next
    INDEX
    Explanations

    position detection and description

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

    The neuron activates on occurrences of the word “position” (i.e. it detects the token “position” wherever it appears).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     famously
    -1.15
     hugely
    -1.11
     astonishing
    -1.08
     wonderfully
    -1.04
     notoriously
    -1.03
     renowned
    -1.00
    廡
    -1.00
    The
    -1.00
     降
    -1.00
     Weird
    -0.99
    POSITIVE LOGITS
     Position
    1.29
     POSITION
    1.28
    nement
    1.26
    sibilities
    1.21
    alised
    1.20
    POSITION
    1.12
    nalités
    1.10
    ophageal
    1.10
    ally
    1.07
    posits
    1.07
    Activations Density 0.029%

    No Known Activations