© 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. 82340
    Prev
    Next
    INDEX
    Explanations

    archway connecting

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

    The neuron strongly activates on words referring to architectural openings—especially “arch,” “archway,” “arches,” and “gateway” in landmark or building descriptions.

    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
    terase
    -0.82
    teng
    -0.75
    btns
    -0.75
    ่านั้น
    -0.73
    UPAC
    -0.71
    ┘
    -0.71
    Btns
    -0.70
    ülerin
    -0.69
     punishable
    -0.68
    独自
    -0.68
    POSITIVE LOGITS
     arch
    3.28
     arches
    2.88
     Arch
    2.61
    arch
    2.41
    Arch
    2.25
     Arches
    2.19
     arched
    1.90
     ARCH
    1.80
     gate
    1.77
     Arc
    1.73
    Activations Density 0.024%

    No Known Activations