© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58877
    Prev
    Next
    INDEX
    Explanations

    preposition followed by the

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

    The neuron strongly activates on numeric tokens and numerical data (digits and decimal numbers) in the text.

    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
     is
    -1.55
     it
    -1.51
     also
    -1.50
     its
    -1.49
     seems
    -1.48
     -
    -1.45
    úcia
    -1.38
     wydaje
    -1.37
     slightly
    -1.37
     or
    -1.33
    POSITIVE LOGITS
    dann
    1.43
     kust
    1.27
     navn
    1.25
    ALWAYS
    1.21
     korban
    1.20
    ﺔ
    1.20
    ZZZZ
    1.19
    cluding
    1.19
     GRAND
    1.17
    POSIX
    1.16
    Activations Density 0.251%

    No Known Activations