© 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. 92133
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by articles

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

    The neuron fires strongly on common little German words—especially prepositions (e.g. auf, mit, bei, in, von, um).

    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
     also
    -1.21
     ursprüng
    -1.05
     οποία
    -1.03
     being
    -1.02
     because
    -1.02
    していました
    -1.00
     ваших
    -1.00
    潸
    -0.99
    してました
    -0.99
     when
    -0.99
    POSITIVE LOGITS
     the
    1.91
    珦
    1.20
     các
    1.16
    Ῥ
    1.07
    ྄
    1.04
    ごめん
    1.02
     a
    1.02
    tably
    1.00
    ┿
    1.00
     our
    1.00
    Activations Density 0.004%

    No Known Activations