© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10856
    Prev
    Next
    INDEX
    Explanations

    in followed by word

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

    The neuron is primarily detecting the word “in” (the preposition appearing as a standalone token).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     as
    -2.28
     what
    -1.91
     through
    -1.79
     using
    -1.67
     one
    -1.66
     is
    -1.65
     with
    -1.59
     putting
    -1.56
     trying
    -1.53
     an
    -1.52
    POSITIVE LOGITS
     indivíduos
    1.55
     позволит
    1.44
     créer
    1.44
     recaudación
    1.43
     destes
    1.41
    も多く
    1.40
     trabalhadores
    1.39
    給你
    1.37
     данного
    1.34
     durer
    1.34
    Activations Density 0.083%

    No Known Activations