© 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. 22-GEMMASCOPE-RES-131K
    7. 53973
    Prev
    Next
    INDEX
    Explanations

    in ways

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

    The neuron overwhelmingly activates on occurrences of the preposition “in.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     these
    -1.44
     of
    -1.21
     since
    -1.16
     your
    -1.13
    aglia
    -1.12
     after
    -1.09
     participado
    -1.08
    RICULUM
    -1.05
    หรือ
    -1.02
    jamos
    -1.02
    POSITIVE LOGITS
     ways
    1.55
     way
    1.43
     manner
    1.19
     manière
    1.12
     façon
    1.08
     sposób
    1.05
     lewat
    1.01
     же
    1.00
    形で
    0.98
    ...
    0.98
    Activations Density 0.081%

    No Known Activations