© 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. 25975
    Prev
    Next
    INDEX
    Explanations

    inter-compounds

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

    The neuron fires strongly on the substring “inter” when it appears as part of longer words (e.g. intercity, interplanetary, intervertebral).

    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
     Thunder
    -0.73
     世界
    -0.73
    ulturally
    -0.73
     Frey
    -0.71
    хом
    -0.71
     Nicole
    -0.69
     Func
    -0.69
     Ferry
    -0.68
     Dre
    -0.67
    世界
    -0.67
    POSITIVE LOGITS
    städ
    0.89
     city
    0.81
     اض
    0.76
     interstellar
    0.75
    耘
    0.74
    interop
    0.70
     książ
    0.69
     ciudades
    0.68
    city
    0.68
     planetary
    0.67
    Activations Density 0.084%

    No Known Activations